session-detail
Shows detailed information about a Claude Code session, including a session summary, associated tasks, and conversation messages (token/model/tool usage shown as a brief part of this overview). Use when the user says "show session", "session details", "what happened in session X". For a dedicated token-usage/cost/model breakdown only, use session-stats instead. If the session is only described by topic/content and not yet identified, use session-search first.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-15
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- session-detail
- description
- Shows detailed information about a Claude Code session, including a session summary, associated tasks, and conversation messages (token/model/tool usage shown as a brief part of this overview). Use when the user says "show session", "session details", "what happened in session X". For a dedicated token-usage/cost/model breakdown only, use session-stats instead. If the session is only described by topic/content and not yet identified, use session-search first.
- allowed-tools
- Bash(python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session_store.py":*) Bash(python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session_transcript.py":*)
02 资源文件 1
- 脚本scripts/smoke_test.py7.8 KB
03 SKILL.md 正文
Session Detail
Show comprehensive details about a single session.
When to Use
- Wants the full picture of one session: summary, tasks, and message transcript
- "show session", "session details", "what happened in session X"
When NOT to Use
- A dedicated token-usage/cost/model breakdown only, not the full profile → use
session-statsinstead - Cross-session task aggregation → use
session-tasksinstead - The target session isn't yet identified — described by content/topic rather than an ID or clear
reference (e.g. "what happened in the session where I fixed the login bug") → use
session-searchfirst to locate it; usesession-detailonce a specific session is identified. - Wants a portable recovery document for a different session, not live detail here → use
session-resumeinstead. - Wants a comparison between two sessions, not detail on one → use
session-diffinstead. - Wants only a bare chronological, event-by-event timeline for one session (no summary or task
context) → use
session-timeline's single-session mode (its Step 1, Option B) instead. - Wants a file/transcript export, not detail shown in the conversation → use
session-exportinstead.
Step 1: Get session detail
If no session ID is given, resolve the live session directly (safe even when the current working directory doesn't match where the session actually started — e.g. a worktree created mid-session):
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session_store.py" current
Otherwise:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session_store.py" session-detail <session-id>
This returns: session summary (including the path field), token usage (input/output/cache), models used, tools called, and associated task lists with their tasks. This command always prints JSON — no --format flag needed.
Step 2: Present summary
Show a formatted summary:
- Session: ID, project, date, duration
- Tokens: input, output, cache read, cache create
- Models: which models were used and how many turns each
- Tools: top tools used with counts
- Tasks: associated task lists and task status summary
Note on resumed sessions
If is_resumed is true in the stats, this session was started via claude --resume or claude --continue. The JSONL only contains messages from the resumed portion — earlier context from the parent session is not included. Mention this to the user so they understand why the transcript may appear to start mid-conversation.
Step 3: Show messages (optional)
If the user wants to see the conversation, use the path field from Step 1's session object:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session_transcript.py" messages <session-path> --limit 20
For more messages, increase --offset and --limit:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session_transcript.py" messages <session-path> --offset 20 --limit 20
To include tool call details:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session_transcript.py" messages <session-path> --include-tools --limit 20
Testing & Validation
Eval suite: evals/session-detail/ — 3 scenarios, skill-tester Quick Workflow blind comparison, all
passed. Eval 3 verified a cross-session task query correctly redirects to session-tasks instead of
being answered directly.
Last dated run record: evals/session-detail/workspace/iteration-2/eval-{1,2,3}/with_skill/grading.json,
2026-09-03. scripts/smoke_test.py structural self-check also passing as of the same date.
Verify this skill activates on:
- "show session details for X"
- "what happened in session X"
- "give me the full picture of this session"
Verify it does NOT activate on:
- "how many tokens did this session use" (narrow usage only) →
session-stats - "what tasks are pending across my sessions" →
session-tasks - "what happened in the session where I fixed the login bug" (session identified by content, not yet
located) →
session-search
Quality gates:
- [ ]
<session-path>in Step 3 is explicitly derived from Step 1'ssession.pathfield
04 同仓库更多 Skills
demo
Fixture skill used by scripts.marketplace_ci sync tests.
export-demo
Fixture skill used by scripts.marketplace_ci export tests.
work-to-development
Validate an accepted Linear Issue's readiness for implementation (criteria, dependencies, duplicate/existing artifacts) and request governed branch/worktree creation through git-kit:starting-work — recording work-started Git/GitHub evidence and a deliberate Linear Started transition only after Git identity is read back and verified. Use when asked to start work on a Linear issue, begin development for an accepted issue, or prepare an accepted issue for implementation. Never creates a branch directly — always delegates to git-kit.
work-linking
Create and maintain stable cross-system links and authority labels between Notion and Linear records, and detect/repair drift between them. Use when asked to link a Notion record to a Linear record, check for drift between Notion and Linear, or repair a broken/stale link. Repairs only the bounded non-authoritative copy or link — never chooses by newest timestamp, and never creates a reverse-write loop against either system's own authority.
status-and-learning
Produce a dated, explicitly non-live Linear-to-Notion progress summary, or capture an outcome/learning after work completes. Use when asked to summarize progress to Notion, report portfolio status, or capture what was learned from a completed piece of work — not to disposition open follow-up items (see open-item-management for that). Never runs automatically or continuously — every summary is a deliberate, approved snapshot, not a live sync.
repository-gates
Discover, delegate, record, and invalidate this repository's actual Git/GitHub lifecycle gates (pre-commit, pre-push, PR required checks, Codex delta review, review requirements, merge rights) and the repository-policy provider profile that maps governed operations to git-kit. Use when asked what gates apply to this repository, to discover repository policy before starting Wave 2 work, or to check whether prior gate evidence is still valid after new commits. Discovery and delegation only — never executes a gate's own internal logic, and never invents a gate the repository doesn't actually define (in particular, never assumes a "Review Changes" gate exists).