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.
git clone --depth 1 https://github.com/roomi-fields/paper-trailWrote 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/commands/roomi-fields/paper-trail/paper-trail-doctor)<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-doctor"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-doctor/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/commands/roomi-fields/paper-trail/paper-trail-doctor"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-doctor.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 | $0.00045 | $0.00563 |
| Opus 5 | $0.00023 | $0.00282 |
| Sonnet 5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
paper-trail-doctor 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 10d 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
/paper-trail:doctor — Run invariants audit
Invoke the registry-doctor skill to check the 19 invariants on the
registry.
Usage
/paper-trail:doctor # full check, severity ≥ info
/paper-trail:doctor --severity error # errors only
/paper-trail:doctor --severity warn # errors + warnings
/paper-trail:doctor --fix # apply safe auto-fixes
/paper-trail:doctor --fix --severity warn # idem
/paper-trail:doctor --json # machine-readable output
/paper-trail:doctor --correlate-rtfm # Couche 5 — RTFM crosscheck
/paper-trail:doctor --check-sha # slow — recompute all sha256
What it does
Delegates to the worker B :
python -m pipeline doctor [flags]
Returns a markdown (or JSON) report classifying violations by invariant and severity. Safe auto-fixes :
- I4 : strip prefix
10_SOURCES/frompdf_pathif present - I6 : recompute
pdf_sha256from disk file if missing or malformed - I9 : renumber
acquisition_attempts[].nto be strictly 1..N - I5 semi : if PDF missing on disk, transition to
needs_reacquisition - I7 semi : if
page1_validation_loginconsistent, transition toneeds_reacquisition
Never auto-fixes (require human decision) :
- I10 : empty
blocked_reason— humain must categorize the blockage - I8 : non-monotonic
state_history— likely a bug or migration artifact - I14 : transition out of terminal state — likely a manual mutation needing audit
Exit code
0: no errors (warns/infos may be present)1: at least one ERROR remaining (after auto-fixes if--fix)
Useful for CI / pre-commit hooks.
Cross-reference
See also :
/paper-trail:status— overall registry state counts/paper-trail:cascade— push refs forward (which doctor will audit)pipeline/USAGE.mdfor the underlying worker B CLI
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.
- 10d ago First seen · 63 lines · 45 tokens per session scan A 04da4a7ba280
paper-trail-doctor is a command published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 7d ago), licensed MIT. It adds 45 tokens to every session and 563 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 commands, from other repositories
gh-security-review
Use to perform a dedicated security review of current branch changes before pushing.
gh-release
Create a new release for the marketplace or a specific plugin.
ledger-research
Launch parallel evidence collection across all active research pillars.
ledger-spec
Generate constrained PRD and architecture documents where every section cites decisions.
quick-research
Quick research with source verification (lighter than /deep-research).
gh-status
Quick overview of current GitHub workflow state.