[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVZXCPFYBW0F8YN4W43GYD":3,"skill-same:01M7AVZXCPFYBW0F8YN4W43GYD":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7AVZXCPFYBW0F8YN4W43GYD","pre-commit-security-guard",null,"Shift security left by intercepting vulnerabilities and secrets before pull requests using Git pre-commit hooks, multi-file DevSkim SAST, Gitleaks, deliberate failure injection, and dual-gate CI enforcement. Do not use for dynamic penetration testing or cloud container runtime audits.","SpectreDeath\u002FBrain-Harness","SpectreDeath","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F207463416?v=4","01M7AVGR1D4X8ADT47APKGVH2Z","JL","01M7AVGR2HSGD23BA5DBTJJTVN",0,"MIT","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpre-commit-security-guard\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pre-commit-security-guard\ndescription: Shift security left by intercepting vulnerabilities and secrets before pull requests using Git pre-commit hooks, multi-file DevSkim SAST, Gitleaks, deliberate failure injection, and dual-gate CI enforcement. Do not use for dynamic penetration testing or cloud container runtime audits.\n---\n\n# Pre-Commit Security Guard: Shift-Left SAST & Secret Interception\n\nThe `pre-commit-security-guard` skill provides the definitive engineering framework for intercepting security vulnerabilities, insecure API usages, and exposed credentials on developer workstations before code ever reaches pull requests, CI runners, or production Git branches.\n\nSynthesizing Umair Mirza's foundational methodology (*\"How to Catch Security Vulnerabilities in Code Before They Reach Your Pull Requests\"*, freeCodeCamp, 2026), this skill establishes a **dual-scanner defense**: pairing Microsoft CST's lightweight static application security testing (SAST) linter **DevSkim** with the dedicated high-entropy credential scanner **Gitleaks**, governed through Git pre-commit hooks, verified with deliberate failure smoke tests, and backed by mandatory CI SARIF reporting.\n\n```\n[1. Toolchain & Division of Labor] -> [2. Dispatcher & Hook Config] -> [3. Deliberate Failure Smoke] -> [4. Triage & Suppression] -> [5. Dual-Gate CI Defense]\n```\n\nSee [CARD.md](CARD.md) for the companion quick-reference card, 5-stage matrix, and verification checklist.\nConsult [crafting-skills](..\u002Fcrafting-skills\u002FSKILL.md) for skill authoring standards and [epistemic-isnad-audit](..\u002Fepistemic-isnad-audit\u002FSKILL.md) for source provenance.\n\n---\n\n## 1. Multi-Engine Toolchain Provisioning & Division of Labor\n\nA robust shift-left security architecture requires strict separation of concerns between code-pattern linting and credential entropy analysis.\n\n1. **Enforce Scanner Division of Labor**:\n   - **DevSkim CLI (Microsoft CST)**: Fast, developer-facing SAST linter. Inspects AST and lexical tokens for insecure cryptography (MD5, SHA1), dangerous API calls, insecure deserialization, command injections, and weak TLS configurations. DevSkim is *not* a secret scanner.\n   - **Gitleaks**: Dedicated secret scanner. Uses regex patterns tuned for token shapes and Shannon entropy calculations to catch API keys, private tokens, passwords, and connection strings that slip past linters.\n2. **Provision Local Toolchain**:\n   - Install `pre-commit`:\n     ```bash\n     pip install pre-commit\n     ```\n   - Install DevSkim CLI as a .NET global tool or download the platform binary:\n     ```bash\n     dotnet tool install --global Microsoft.CST.DevSkim.CLI\n     ```\n   - Verify toolchain installation:\n     ```bash\n     pre-commit --version\n     devskim --version\n     ```\n\n> **Completion criterion**: Pre-commit, DevSkim CLI, and Gitleaks available in path; division of labor between SAST linting and secret detection documented.\n\n---\n\n## 2. Pre-Commit Configuration & Multi-File Execution Dispatcher\n\nDevSkim's CLI accepts a single target path via `-I`, whereas `pre-commit` appends all staged files as trailing command-line arguments. Passing multiple files directly breaks standard CLI invocation.\n\n1. **Scaffold Python Multi-File Dispatcher (`scripts\u002Frun-devskim.py`)**:\n   ```python\n   import subprocess\n   import sys\n\n   exit_code = 0\n   for filename in sys.argv[1:]:\n       result = subprocess.run([\"devskim\", \"analyze\", \"-I\", filename])\n       exit_code = exit_code or result.returncode\n\n   sys.exit(exit_code)\n   ```\n2. **Configure `.pre-commit-config.yaml`**:\n   ```yaml\n   repos:\n     - repo: local\n       hooks:\n         - id: devskim\n           name: DevSkim security lint\n           entry: python scripts\u002Frun-devskim.py\n           language: system\n           types_or: [python, javascript, typescript, json, yaml]\n           pass_filenames: true\n\n     - repo: https:\u002F\u002Fgithub.com\u002Fgitleaks\u002Fgitleaks\n       rev: v8.30.1\n       hooks:\n         - id: gitleaks\n   ```\n3. **Bind Git Hooks**:\n   ```bash\n   pre-commit install\n   ```\n\n> **Completion criterion**: Dispatcher script authored, `.pre-commit-config.yaml` declared with `pass_filenames: true`, and `.git\u002Fhooks\u002Fpre-commit` active.\n\n---\n\n## 3. Deliberate Synthetic Failure Verification\n\nNever trust a security guardrail without verifying that it actively blocks commits.\n\n1. **Smoke-Test SAST Hook (Insecure Cryptography)**:\n   - Create a temporary fixture (`test_insecure.js` or `test_insecure.py`):\n     ```javascript\n     const crypto = require(\"crypto\");\n     const hash = crypto.createHash(\"md5\").update(\"password\").digest(\"hex\");\n     ```\n   - Stage and attempt to commit:\n     ```bash\n     git add test_insecure.js\n     git commit -m \"test: verify devskim hook failure\"\n     ```\n   - **Assert**: DevSkim rejects commit with non-zero exit code (Exit 1) and outputs rule diagnostic (`DS126858: Weak Hash Algorithm`).\n2. **Smoke-Test Secret Scanner (Entropy \u002F Key Detection)**:\n   - Stage a shaped synthetic API key:\n     ```javascript\n     const apiKey = \"4f2a9c1e7b6d3a8f0c5e9b2d7a41c6\";\n     ```\n   - **Assert**: Gitleaks rejects commit with exit code 1, reporting leak detection.\n3. **Post-Test Cleanup**:\n   - Remove temporary test fixtures immediately. **Never use real credentials for testing.**\n\n### The Visual Brief & Stakeholder Alignment\n\nWhen onboarding repositories or aligning with engineering teams, generate an interactive visual brief in `%TEMP%\\pre-commit-security-guard-\u003Ctimestamp>.html` rendering the dual-scanner architecture DAG, failure smoke test matrices, and diagnostic scorecards using Mermaid.js and Tailwind CSS.\n\n### Mandatory Checkpoint Gate\n\nBefore enabling blocking hooks on shared or production repositories, present an implementation plan with `RequestFeedback: true` confirming scanner parameters, legacy baseline results, and deliberate synthetic failure verification. **STOP and obtain stakeholder confirmation** before committing hooks to repository branches.\n\n> **Completion criterion**: Both hooks independently confirmed to block commits with non-zero exit codes against synthetic failure fixtures; visual brief rendered in %TEMP% and mandatory checkpoint confirmed.\n\n---\n\n## 4. Progressive Triage, Suppression Hygiene & Legacy Baselines\n\nAvoid paralyzing engineering velocity when rolling out hooks to legacy repositories.\n\n1. **Establish Codebase Baseline**:\n   - Run hooks manually against the entire repository once:\n     ```bash\n     pre-commit run --all-files\n     ```\n   - Catalog existing legacy violations without blocking day-to-day feature work.\n2. **Enforce Surgical Inline Suppressions**:\n   - When a finding is determined to be a benign or unexploitable false positive, suppress only that specific finding with an in-code comment and explicit rationale.\n   - **Strict Negative Boundary**: Never apply blanket directory exclusions (e.g. `exclude: src\u002F.*`). Broad directory exclusions create permanent blind spots.\n3. **Preserve Sub-3s Hook Latency**:\n   - Keep local pre-commit checks strictly focused on staged files (`pass_filenames: true`). Reserve full-repository audits for CI pipelines.\n\n> **Completion criterion**: Legacy findings cataloged, inline suppressions documented with rationale, and zero blanket directory exclusions present.\n\n---\n\n## 5. Dual-Gate CI Defense & SARIF Security Governance\n\nLocal pre-commit hooks provide immediate developer feedback, but they can be bypassed with `git commit --no-verify`. Security enforcement must be duplicated in CI.\n\n1. **Author GitHub Actions Workflow (`.github\u002Fworkflows\u002Fsecurity.yml`)**:\n   ```yaml\n   name: Security Checks\n\n   on:\n     pull_request:\n     push:\n       branches: [main]\n\n   jobs:\n     scan:\n       runs-on: ubuntu-latest\n       permissions:\n         contents: read\n         security-events: write\n       steps:\n         - uses: actions\u002Fcheckout@v4\n           with:\n             fetch-depth: 0\n\n         - uses: actions\u002Fsetup-dotnet@v4\n           with:\n             dotnet-version: \"8.0.x\"\n\n         - name: Install DevSkim\n           run: dotnet tool install --global Microsoft.CST.DevSkim.CLI\n\n         - name: Run DevSkim SARIF\n           run: devskim analyze -I . -f sarif -O devskim.sarif\n\n         - name: Upload DevSkim SARIF\n           uses: github\u002Fcodeql-action\u002Fupload-sarif@v3\n           if: always()\n           with:\n             sarif_file: devskim.sarif\n\n         - name: Run Gitleaks Full History Audit\n           uses: gitleaks\u002Fgitleaks-action@v2\n           env:\n             GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}\n   ```\n2. **Audit Parameters**:\n   - `fetch-depth: 0`: Guarantees Gitleaks inspects all historical commits rather than just the PR tip.\n   - `upload-sarif`: Routes SAST findings into the GitHub repository Security tab for triage and tracking.\n\n> **Completion criterion**: CI workflow committed, running Gitleaks with `fetch-depth: 0` and uploading DevSkim SARIF findings to GitHub Security.\n\n---\n\n## Diagnostic Evaluation Scorecard\n\n| # | Evaluation Axis | Diagnostic Inquiry | Passing Gate | Verification Method |\n|---|---|---|---|---|\n| 1 | **Dual-Scanner Partitioning** | Are SAST linting (DevSkim) and secret scanning (Gitleaks) split into specialized hooks? | Both hooks declared in config | Review `.pre-commit-config.yaml` |\n| 2 | **Multi-File Dispatcher** | Does the setup handle multiple staged files without crashing on single-arg CLI limits? | Python loop wrapper active | Test with multiple staged files |\n| 3 | **Deliberate Smoke Test** | Have both hooks been verified to block commits using deliberate synthetic failures? | Both SAST and secrets exit 1 | Smoke test with MD5 and test key |\n| 4 | **Suppression Hygiene** | Are false positives handled via surgical inline comments rather than folder exclusions? | Zero blanket folder exclusions | Inspect config for broad excludes |\n| 5 | **Dual-Gate CI Parity** | Does remote CI enforce full history secret checks (`fetch-depth: 0`) and SARIF reporting? | CI workflow active in PR gate | Verify `.github\u002Fworkflows\u002Fsecurity.yml` |\n\n---\n\n## Anti-Patterns\n\n- **Secret-Linter Conflation** — Relying solely on DevSkim for secret detection, allowing subtle or high-entropy API tokens to leak into commits.\n- **Whole-Repo Local Scanning** — Running `devskim analyze -I .` on every commit in a large repo, causing unacceptable developer latency and hook bypasses.\n- **Blanket Directory Exclusions** — Masking false positives by excluding entire folders (e.g. `src\u002F` or `tests\u002F`) rather than suppressing specific rule IDs.\n- **Client-Only Security Reliance** — Failing to enforce security checks in CI, allowing `git commit --no-verify` to push vulnerabilities directly to the remote repository.\n- **Unverified Hook Deployment** — Rolling out pre-commit hooks without executing synthetic failure verification for both SAST and credential gates.\n- **Real-Secret Verification** — Using actual production or test credentials to verify scanner blocking instead of synthetic high-entropy dummy strings.\n","# Pre-Commit Security Guard: Shift-Left SAST & Secret Interception\n\nThe `pre-commit-security-guard` skill provides the definitive engineering framework for intercepting security vulnerabilities, insecure API usages, and exposed credentials on developer workstations before code ever reaches pull requests, CI runners, or production Git branches.\n\nSynthesizing Umair Mirza's foundational methodology (*\"How to Catch Security Vulnerabilities in Code Before They Reach Your Pull Requests\"*, freeCodeCamp, 2026), this skill establishes a **dual-scanner defense**: pairing Microsoft CST's lightweight static application security testing (SAST) linter **DevSkim** with the dedicated high-entropy credential scanner **Gitleaks**, governed through Git pre-commit hooks, verified with deliberate failure smoke tests, and backed by mandatory CI SARIF reporting.\n\n```\n[1. Toolchain & Division of Labor] -> [2. Dispatcher & Hook Config] -> [3. Deliberate Failure Smoke] -> [4. Triage & Suppression] -> [5. Dual-Gate CI Defense]\n```\n\nSee [CARD.md](CARD.md) for the companion quick-reference card, 5-stage matrix, and verification checklist.\nConsult [crafting-skills](..\u002Fcrafting-skills\u002FSKILL.md) for skill authoring standards and [epistemic-isnad-audit](..\u002Fepistemic-isnad-audit\u002FSKILL.md) for source provenance.\n\n---\n\n## 1. Multi-Engine Toolchain Provisioning & Division of Labor\n\nA robust shift-left security architecture requires strict separation of concerns between code-pattern linting and credential entropy analysis.\n\n1. **Enforce Scanner Division of Labor**:\n   - **DevSkim CLI (Microsoft CST)**: Fast, developer-facing SAST linter. Inspects AST and lexical tokens for insecure cryptography (MD5, SHA1), dangerous API calls, insecure deserialization, command injections, and weak TLS configurations. DevSkim is *not* a secret scanner.\n   - **Gitleaks**: Dedicated secret scanner. Uses regex patterns tuned for token shapes and Shannon entropy calculations to catch API keys, private tokens, passwords, and connection strings that slip past linters.\n2. **Provision Local Toolchain**:\n   - Install `pre-commit`:\n     ```bash\n     pip install pre-commit\n     ```\n   - Install DevSkim CLI as a .NET global tool or download the platform binary:\n     ```bash\n     dotnet tool install --global Microsoft.CST.DevSkim.CLI\n     ```\n   - Verify toolchain installation:\n     ```bash\n     pre-commit --version\n     devskim --version\n     ```\n\n> **Completion criterion**: Pre-commit, DevSkim CLI, and Gitleaks available in path; division of labor between SAST linting and secret detection documented.\n\n---\n\n## 2. Pre-Commit Configuration & Multi-File Execution Dispatcher\n\nDevSkim's CLI accepts a single target path via `-I`, whereas `pre-commit` appends all staged files as trailing command-line arguments. Passing multiple files directly breaks standard CLI invocation.\n\n1. **Scaffold Python Multi-File Dispatcher (`scripts\u002Frun-devskim.py`)**:\n   ```python\n   import subprocess\n   import sys\n\n   exit_code = 0\n   for filename in sys.argv[1:]:\n       result = subprocess.run([\"devskim\", \"analyze\", \"-I\", filename])\n       exit_code = exit_code or result.returncode\n\n   sys.exit(exit_code)\n   ```\n2. **Configure `.pre-commit-config.yaml`**:\n   ```yaml\n   repos:\n     - repo: local\n       hooks:\n         - id: devskim\n           name: DevSkim security lint\n           entry: python scripts\u002Frun-devskim.py\n           language: system\n           types_or: [python, javascript, typescript, json, yaml]\n           pass_filenames: true\n\n     - repo: https:\u002F\u002Fgithub.com\u002Fgitleaks\u002Fgitleaks\n       rev: v8.30.1\n       hooks:\n         - id: gitleaks\n   ```\n3. **Bind Git Hooks**:\n   ```bash\n   pre-commit install\n   ```\n\n> **Completion criterion**: Dispatcher script authored, `.pre-commit-config.yaml` declared with `pass_filenames: true`, and `.git\u002Fhooks\u002Fpre-commit` active.\n\n---\n\n## 3. Deliberate Synthetic Failure Verification\n\nNever trust a security guardrail without verifying that it actively blocks commits.\n\n1. **Smoke-Test SAST Hook (Insecure Cryptography)**:\n   - Create a temporary fixture (`test_insecure.js` or `test_insecure.py`):\n     ```javascript\n     const crypto = require(\"crypto\");\n     const hash = crypto.createHash(\"md5\").update(\"password\").digest(\"hex\");\n     ```\n   - Stage and attempt to commit:\n     ```bash\n     git add test_insecure.js\n     git commit -m \"test: verify devskim hook failure\"\n     ```\n   - **Assert**: DevSkim rejects commit with non-zero exit code (Exit 1) and outputs rule diagnostic (`DS126858: Weak Hash Algorithm`).\n2. **Smoke-Test Secret Scanner (Entropy \u002F Key Detection)**:\n   - Stage a shaped synthetic API key:\n     ```javascript\n     const apiKey = \"4f2a9c1e7b6d3a8f0c5e9b2d7a41c6\";\n     ```\n   - **Assert**: Gitleaks rejects commit with exit code 1, reporting leak detection.\n3. **Post-Test Cleanup**:\n   - Remove temporary test fixtures immediately. **Never use real credentials for testing.**\n\n### The Visual Brief & Stakeholder Alignment\n\nWhen onboarding repositories or aligning with engineering teams, generate an interactive visual brief in `%TEMP%\\pre-commit-security-guard-\u003Ctimestamp>.html` rendering the dual-scanner architecture DAG, failure smoke test matrices, and diagnostic scorecards using Mermaid.js and Tailwind CSS.\n\n### Mandatory Checkpoint Gate\n\nBefore enabling blocking hooks on shared or production repositories, present an implementation plan with `RequestFeedback: true` confirming scanner parameters, legacy baseline results, and deliberate synthetic failure verification. **STOP and obtain stakeholder confirmation** before committing hooks to repository branches.\n\n> **Completion criterion**: Both hooks independently confirmed to block commits with non-zero exit codes against synthetic failure fixtures; visual brief rendered in %TEMP% and mandatory checkpoint confirmed.\n\n---\n\n## 4. Progressive Triage, Suppression Hygiene & Legacy Baselines\n\nAvoid paralyzing engineering velocity when rolling out hooks to legacy repositories.\n\n1. **Establish Codebase Baseline**:\n   - Run hooks manually against the entire repository once:\n     ```bash\n     pre-commit run --all-files\n     ```\n   - Catalog existing legacy violations without blocking day-to-day feature work.\n2. **Enforce Surgical Inline Suppressions**:\n   - When a finding is determined to be a benign or unexploitable false positive, suppress only that specific finding with an in-code comment and explicit rationale.\n   - **Strict Negative Boundary**: Never apply blanket directory exclusions (e.g. `exclude: src\u002F.*`). Broad directory exclusions create permanent blind spots.\n3. **Preserve Sub-3s Hook Latency**:\n   - Keep local pre-commit checks strictly focused on staged files (`pass_filenames: true`). Reserve full-repository audits for CI pipelines.\n\n> **Completion criterion**: Legacy findings cataloged, inline suppressions documented with rationale, and zero blanket directory exclusions present.\n\n---\n\n## 5. Dual-Gate CI Defense & SARIF Security Governance\n\nLocal pre-commit hooks provide immediate developer feedback, but they can be bypassed with `git commit --no-verify`. Security enforcement must be duplicated in CI.\n\n1. **Author GitHub Actions Workflow (`.github\u002Fworkflows\u002Fsecurity.yml`)**:\n   ```yaml\n   name: Security Checks\n\n   on:\n     pull_request:\n     push:\n       branches: [main]\n\n   jobs:\n     scan:\n       runs-on: ubuntu-latest\n       permissions:\n         contents: read\n         security-events: write\n       steps:\n         - uses: actions\u002Fcheckout@v4\n           with:\n             fetch-depth: 0\n\n         - uses: actions\u002Fsetup-dotnet@v4\n           with:\n             dotnet-version: \"8.0.x\"\n\n         - name: Install DevSkim\n           run: dotnet tool install --global Microsoft.CST.DevSkim.CLI\n\n         - name: Run DevSkim SARIF\n           run: devskim analyze -I . -f sarif -O devskim.sarif\n\n         - name: Upload DevSkim SARIF\n           uses: github\u002Fcodeql-action\u002Fupload-sarif@v3\n           if: always()\n           with:\n             sarif_file: devskim.sarif\n\n         - name: Run Gitleaks Full History Audit\n           uses: gitleaks\u002Fgitleaks-action@v2\n           env:\n             GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}\n   ```\n2. **Audit Parameters**:\n   - `fetch-depth: 0`: Guarantees Gitleaks inspects all historical commits rather than just the PR tip.\n   - `upload-sarif`: Routes SAST findings into the GitHub repository Security tab for triage and tracking.\n\n> **Completion criterion**: CI workflow committed, running Gitleaks with `fetch-depth: 0` and uploading DevSkim SARIF findings to GitHub Security.\n\n---\n\n## Diagnostic Evaluation Scorecard\n\n| # | Evaluation Axis | Diagnostic Inquiry | Passing Gate | Verification Method |\n|---|---|---|---|---|\n| 1 | **Dual-Scanner Partitioning** | Are SAST linting (DevSkim) and secret scanning (Gitleaks) split into specialized hooks? | Both hooks declared in config | Review `.pre-commit-config.yaml` |\n| 2 | **Multi-File Dispatcher** | Does the setup handle multiple staged files without crashing on single-arg CLI limits? | Python loop wrapper active | Test with multiple staged files |\n| 3 | **Deliberate Smoke Test** | Have both hooks been verified to block commits using deliberate synthetic failures? | Both SAST and secrets exit 1 | Smoke test with MD5 and test key |\n| 4 | **Suppression Hygiene** | Are false positives handled via surgical inline comments rather than folder exclusions? | Zero blanket folder exclusions | Inspect config for broad excludes |\n| 5 | **Dual-Gate CI Parity** | Does remote CI enforce full history secret checks (`fetch-depth: 0`) and SARIF reporting? | CI workflow active in PR gate | Verify `.github\u002Fworkflows\u002Fsecurity.yml` |\n\n---\n\n## Anti-Patterns\n\n- **Secret-Linter Conflation** — Relying solely on DevSkim for secret detection, allowing subtle or high-entropy API tokens to leak into commits.\n- **Whole-Repo Local Scanning** — Running `devskim analyze -I .` on every commit in a large repo, causing unacceptable developer latency and hook bypasses.\n- **Blanket Directory Exclusions** — Masking false positives by excluding entire folders (e.g. `src\u002F` or `tests\u002F`) rather than suppressing specific rule IDs.\n- **Client-Only Security Reliance** — Failing to enforce security checks in CI, allowing `git commit --no-verify` to push vulnerabilities directly to the remote repository.\n- **Unverified Hook Deployment** — Rolling out pre-commit hooks without executing synthetic failure verification for both SAST and credential gates.\n- **Real-Secret Verification** — Using actual production or test credentials to verify scanner blocking instead of synthetic high-entropy dummy strings.\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Fpre-commit-security-guard","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness","https:\u002F\u002Fgithub.com\u002FSpectreDeath","I'm here to manage stress so I wouldn't expect earth shattering break throughs I'm just an enthusiast that likes making stuff. ","2026-11-15 05:32:58",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add SpectreDeath\u002FBrain-Harness --skill pre-commit-security-guard",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill pre-commit-security-guard",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill pre-commit-security-guard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpre-commit-security-guard\u002FSKILL.md",true,[45,51,55,61],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",4074,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpre-commit-security-guard\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",602,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpre-commit-security-guard\u002Fconfig.default.yaml",{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Fpre_commit_security_engine.py","SCRIPT","脚本",35134,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpre-commit-security-guard\u002Fscripts\u002Fpre_commit_security_engine.py",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Frun-devskim.py",2018,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpre-commit-security-guard\u002Fscripts\u002Frun-devskim.py",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7E0W6FR68J2N9CXCZTAQJFX","ui-behavior-primitive-architect","Architect, audit, and verify zero-dependency headless UI behavior primitives, WebMCP agent bridges, WAI-ARIA\u002FSSR\u002FRTL tri-modal checks, and framework expert routing. Do not use for static CSS theme styling or backend database migrations.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fui-behavior-primitive-architect\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7E0VZ7JQNW34G271DENFGYP","trustgraph-ontology-governor","Govern knowledge graphs, SHACL-AF triple policies, OntologyRAG subclass validation, PROV-O dual named graphs, and Laya entropy decision scoring. Do not use for relational SQL queries or generic web scraping.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftrustgraph-ontology-governor\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7E0VQ6Z7R45Q8QAZ4MT39EK","shim-harness-governor","Govern universal CLI agent loops, 4-tier tool permissions, ancestor-symlink workspace sandboxes, deterministic-first command routing, collision-safe MCP namespacing, and layered skill loading. Do not use for static UI styling or external SQL analytics.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshim-harness-governor\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7E0VC18NMP1QBSRJ3TPQ7MB","graphiti-zep-memory-governor","Govern bi-temporal knowledge graphs with Graphiti future-edge clamping, MinHash\u002FLSH entity dedup, RRF\u002FMMR reranking, and Zep typed ontologies. Do not use for static SQL joins or generic web crawling.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7E0V12ABE1RW3ZRCST8VH5Z","agora-mcp-workbench-architect","Architect, audit, and orchestrate Agora Workbench MCP servers, loopback sidecars, unified state graphs, gateway\u002Fdispatcher connectors, and policy-enforced data lakes. Do not use for static frontend CSS styling or non-MCP desktop GUI automation.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagora-mcp-workbench-architect\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7BFYG6QT3484VC57TZ19V7P","skill-eval-assurance-runner","Evaluate and assure agent skills using small-N Wilson confidence intervals, unbiased pass^k reliability, deterministic trajectory graders, preflight boundary honesty, and sealed digest verification. Do not use for subjective prose review or unconstrained production deployment.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-eval-assurance-runner\u002FSKILL.md",[],[]]