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 agentmods add skills/codeinfinity1/stram/audit-trail-reviewnpx skills add CodeInfinity1/Stram --skill audit-trail-reviewgit clone --depth 1 https://github.com/CodeInfinity1/StramWhat 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 | $0.00030 | $0.00385 |
| Opus 5 | $0.00015 | $0.00192 |
| Sonnet 5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
audit-trail-review 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 3d 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.
What it actually says
Audit Trail Review
Purpose
Reconstruct reality from logs and artifacts. This skill helps answer what happened, what was approved, what was sent, what changed, and what remains uncertain.
When To Use
Use when the user asks current status, "did it send", "what changed", "why did this happen", or for compliance/debug audits.
Inputs And Evidence
- Run IDs, approval tokens, outbox IDs, interpreter run IDs, screenshot filenames, commit hashes, and memory events.
Tool Map
channel_outboxpython_interpreter_runspython_interpreter_runscreen_capturesmemory_searchcognitive_statestatus-update-writing
Workflow
- Identify the time window and artifact types.
- Inspect relevant native stores/tools.
- Separate prepared, approved, executed, failed, blocked, and skipped actions.
- Tie claims to IDs/paths/tool results.
- Report missing evidence as missing.
- Recommend cleanup or follow-up if needed.
Native Implementation Boundaries
- Use Stram audit/artifact/status tools.
- Do not import external reference audit-trail plugins.
- Do not infer completion without evidence.
Safety And Approval
- Audit logs may contain sensitive data.
- Redact secrets and private messages.
- Do not delete artifacts unless approved.
Verification
- Cite IDs, paths, commits, or statuses.
- Confirm current worktree/run state.
- Label uncertainty.
Failure Modes
- Relying on memory instead of logs.
- Mixing prepared and sent states.
- Ignoring failed approvals.
References
- Shortlist item:
audit-trail-review.
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.
- 3d ago First seen · 66 lines · 30 tokens per session scan A 9c38ee558c09
audit-trail-review is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 23d ago), licensed MIT. It adds 30 tokens to every session and 385 once invoked, about $0.0002 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
golden-rss
Use when testing the rss golden build.
omh-buzz
This is a Hermes-native buzz workflow skill.
redteam-api-detail-pack
Domain routing and boundary guidance for authorized API security testing, including BOLA/IDOR, authentication bypass, mass assignment, missing rate limits, and GraphQL issues. Use when a task belongs to the API testing domain and needs scope, evidence, pivot, or exit criteria.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…