Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add paultyng/skill-issue --skill audit-historygit clone --depth 1 https://github.com/paultyng/skill-issueWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/paultyng/skill-issue/audit-history)<a href="https://agentmods.dev/skills/paultyng/skill-issue/audit-history"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/audit-history/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paultyng/skill-issue/audit-history"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/audit-history.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.02747 |
| Opus 5 | $0.00027 | $0.01373 |
| Sonnet 5 | $0.00011 | $0.00549 |
| Haiku 4.5 | $0.00005 | $0.00275 |
Grade A, and why
audit-history scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit History
Review past agent sessions and memory files to surface friction patterns, stale memories, and gaps. Synthesize findings into ranked recommendations for new skills, rules, and memory cleanup actions.
Phase 1 -- Discover Sources
Transcripts
Transcripts come from two sources. Both use JSONL format but have different schemas.
Cursor
Cursor agent transcripts live under ~/.cursor/projects/*/agent-transcripts/.
- List all project workspace directories under
~/.cursor/projects/ - For each, list
.jsonlfiles inagent-transcripts/ - Distinguish parent from subagent transcripts: parent transcripts are top-level
.jsonlfiles; subagent transcripts live in subdirectories named by the parent's UUID. Only analyze parent transcripts
Claude Code
Claude Code session transcripts live under ~/.claude/projects/*/sessions/. Project directory names are URL-encoded absolute paths (e.g. %2FUsers%2Fpaul%2Fsrc%2Fmyproject).
- List all project directories under
~/.claude/projects/ - For each, list
.jsonlfiles insessions/
Memory
Memory files live under ~/.claude/projects/*/memory/.
- Scan all project directories for
memory/subdirectories - For each, list
.mdfiles (separate MEMORY.md index from content files) - Also scan
~/.claude/rules/for global rules (needed for duplicate detection)
Inventory
Report the combined inventory before proceeding:
Found N transcripts across M projects, Z memories across P projects:
Cursor (X transcripts):
- project-a: X1 transcripts
Claude Code (Y transcripts, Z memories):
- project-b: Y1 transcripts, Z1 memories (feedback x2, project x1)
- project-c: Y2 transcripts, 0 memories
Global rules: R rules in ~/.claude/rules/
Empty memory directories: [list]
Projects with sessions but no memories: [list]
Phase 2 -- Batch and Dispatch
Launch transcript subagents and memory subagent in parallel.
Each subagent prompt follows subagent-prompt-contract: state the goal in one sentence, paste the file list and extraction schema inline (do not ask the subagent to re-read this SKILL.md), cap the output at the schema below, and prefix the return with the four-state Status line so Phase 3 can branch on it without parsing the body:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 282 lines · 54 tokens per session scan A 1330f3f537f8
audit-history is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 29d ago), licensed MIT. It adds 54 tokens to every session and 2,747 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chatcrystal-task-writeback
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through writetaskmemory or emit a structured memory candidate for later save.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
chatcrystal-task-recall
Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work. Use when the task is non-trivial, has repository or project context, and prior fixes, decisions, pitfalls, or reusable patterns may change the…
workspace-knowledge-sync
Syncs knowledge to the agentic-harness knowledge base and AGENTS.md learned facts. Use when the assistant discovers new patterns, learns user preferences, workspace facts, or identifies information worth preserving for future sessions. Integrates with platform-engineer (formerly tech-assistant) for automatic trigger…
workspace
Scaffold and manage the stateless AI workspace — context, packs, repos, and knowledge for multi-repo orchestration.
memory
Persistent long-term memory system with beliefs, predictions, and knowledge graphs. Use for remembering decisions, learnings, and patterns across sessions.