session-audit SKILL.md skillA

session-audit from foyzulkarim/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add foyzulkarim/skills/session-audit@git:20260904.3b8ccca

Pins git:20260904.3b8ccca in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
foyzulkarim/skills
Path
dev-pipeline/skills/session-audit/SKILL.md
Versions recorded
2
Latest version
git:20260904.3b8ccca, committed Sep 4, 2026
First version recorded
Sep 4, 2026
Size
15,051 bytes
Repository stars
43
License
none declared

Audit Claude Code session logs (~/.claude/projects) for token waste and produce a ranked, attributed efficiency report (habit / skill_file / config). Use when the user asks to audit session efficiency, analyze token waste or cost blowups, review Claude Code usage cost, or asks "where are my tokens going".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Session-Audit

You are the reasoning layer (L2/L3) of a layered audit engine. Bundled deterministic scripts (L0/L1) digest raw session logs into metadata-only artifacts; you reason over aggregates and escalate to content only through a budget-capped fetch interface.

`{base_directory}` below refers to this skill's directory (the convention used by the runtime to inject script paths). Set the workdir once and use it everywhere:

```sh
export AUDIT_WORKDIR=<session scratchpad>/audit_workdir   # working artifacts — ephemeral
```

**Two lifetimes.** The JSON artifacts are intermediates and belong in the ephemeral workdir. The **report is the deliverable and must outlive the session** — it goes to a dated file in a stable, project-independent archive:

```sh
mkdir -p ~/.claude/audit-reports
# final report -> ~/.claude/audit-reports/<YYYY-MM-DD>.md
```

Keeping past reports is also the only way to answer "am I improving?": cross-run persistence is not implemented (I7), so trend comes from comparing today's report to the archive, not from the data layer.

## Invariants (non-negotiable)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add foyzulkarim/skills/session-audit@sha256:7008e75d94bdef8a

The line at the top of this page pins the label git:20260904.3b8ccca, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_oqtj4z5kqmar7jsh.svg)](https://markdownregistry.com/a/art_oqtj4z5kqmar7jsh)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, all committed on Sep 4, 2026.

versioncommittedcommitsizeaudit
git:20260904.3b8ccca latest2026-09-04 3b8ccca 15,051 BA view · diff
git:20260904.36f7fba2026-09-04 36f7fba 15,062 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (15051 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

foyzulkarim/skills · 43 stars · license none declared · pushed 2026-09-04 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_oqtj4z5kqmar7jsh
GET https://markdownregistry.com/api/v1/resolve?ref=foyzulkarim/skills/session-audit
GET https://markdownregistry.com/api/v1/blob/7008e75d94bdef8a4bc77c7493ab0427a44b3247247b5dc6f6852583f05f8a89

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from foyzulkarim/skills

AGENTS.md AGENTS.md file
foyzulkarim/skills · AGENTS.md
git:20260904.8f83398 · audit B · 43 stars
CLAUDE.md CLAUDE.md file
foyzulkarim/skills · CLAUDE.md
git:20260831.b6940c2 · audit A · 43 stars
archive-issue SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/archive-issue/SKILL.md · Retire a closed issue's working artifacts out of specs/ into the GitHub wiki. Use only when the user asks to archive a…
git:20260823.71acb2d · audit A · 43 stars
commit SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/commit/SKILL.md · One-shot conventional commit; bundled scripts adaptively gather diff context, draft the message, and stage+commit —…
git:20260724.cdb1a53 · audit A · 43 stars
execute-qa SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/execute-qa/SKILL.md · Executes a QA specification (specs/qa/QA-<N>-<slug>.md) written by /plan-qa: drives every step with the plan's drivers…
git:20260831.b6940c2 · audit A · 43 stars
finish-worktree SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/finish-worktree/SKILL.md · After an issue's PR has squash-merged on GitHub and its issue has closed: fast-forward the default branch, remove the…
git:20260724.cdb1a53 · audit A · 43 stars
generate-tasks SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/generate-tasks/SKILL.md · Phase 3 of 5 — slices the ARCH doc into verification-ready task specs (tdd/test-after/ui/checklist), emitted as a…
git:20260823.71acb2d · audit A · 43 stars
implement SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/implement/SKILL.md · Phase 4 of 5 — implements tasks from TASKS-<N>-<slug>.md (with ARCH-<N>-<slug>.md as architecture-only context) using…
git:20260823.71acb2d · audit A · 43 stars
move-to-worktree SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/move-to-worktree/SKILL.md · After /start-task: park the current clean, pushed feature branch in its own issue-numbered nested worktree…
git:20260823.71acb2d · audit A · 43 stars
plan-architecture SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/plan-architecture/SKILL.md · Phase 2 of 5 — collaborative system design plus change-footprint mapping; outputs an ARCH doc for generate-tasks. Use…
git:20260823.71acb2d · audit A · 43 stars
plan-qa SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/plan-qa/SKILL.md · Post-implementation QA planning — independent of /review (the developer chooses whether to run them sequentially or in…
git:20260831.b6940c2 · audit A · 43 stars
plan-requirements SKILL.md skill
foyzulkarim/skills · dev-pipeline/skills/plan-requirements/SKILL.md · Phase 1 of 5 — Socratic interview capturing WHAT and WHY; outputs a sprint-sized REQ doc for plan-architecture. Use…
git:20260724.cdb1a53 · audit A · 43 stars

Every file in foyzulkarim/skills

Browse by kind, by grade A, or by owner.