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 Detective-XH/DocGraph --skill policy-drift-auditgit clone --depth 1 https://github.com/Detective-XH/DocGraphWrote 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/detective-xh/docgraph/policy-drift-audit)<a href="https://agentmods.dev/skills/detective-xh/docgraph/policy-drift-audit"><img src="https://agentmods.dev/badge/skills/detective-xh/docgraph/policy-drift-audit/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/detective-xh/docgraph/policy-drift-audit"><img src="https://agentmods.dev/badge/skills/detective-xh/docgraph/policy-drift-audit.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 | $0.00050 | $0.00827 |
| Opus 5 | $0.00025 | $0.00413 |
| Sonnet 5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
policy-drift-audit 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Policy/Process Drift Audit
Invocation — Claude Code:
Skill("policy-drift-audit")| OpenCode / Codex: use triggers above.
Runs the DocGraph policy/process drift audit and presents findings for human review. The audit is advisory — findings highlight candidates for action, not authoritative rulings.
Execution
- Model: Haiku (query) → Sonnet (remediation suggestions if requested)
- Effort: Low
- Advisor: Not required
- Core computation: done by DocGraph's
GetDriftFindingsengine, not by this skill
Step 1: Check index status
docgraph_status
Confirm:
policy_processpack is listed under Domain Packs- Governance metadata is indexed (docs with metadata > 0)
If policy_process is not listed, the binary is too old or the pack was never registered —
tell the user to upgrade DocGraph and run docgraph index --force.
Step 2: Run the drift audit
docgraph_context task="policy/process drift audit" format=drift_audit
This calls DocGraph's GetDriftFindings engine, which checks:
| Code | Meaning |
|---|---|
policy.stale_review |
review_due date has passed; status is not archived/superseded |
policy.superseded_referenced |
A superseded document is still referenced by an active document |
policy.duplicate |
Two approved documents are highly similar (≥ 0.75 similarity) |
policy.non_canonical |
Multiple active documents claim the same canonical_source |
policy.conflicting |
Competing active authorities on the same topic, or conflicting supersedes claims |
Step 3: Present findings to the user
Group findings by severity (errors first, then warnings).
For each finding:
- State the file path(s) and finding code
- Show the message and evidence from the finding
- Suggest a concrete remediation (below) — but do NOT make the change without confirmation
Remediation patterns
| Code | Suggested action |
|---|---|
policy.stale_review |
Update review_due in frontmatter, or change status to archived if retired |
policy.superseded_referenced |
Update the citing document to reference the newer version instead |
policy.duplicate |
Merge or archive one copy; ensure one declares itself canonical_source |
policy.non_canonical |
Resolve which copy is authoritative; archive or update canonical_source on the others |
policy.conflicting |
Determine which document holds authority; update status/supersedes/superseded_by accordingly |
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 · 103 lines · 50 tokens per session scan A ffe14370cc31
policy-drift-audit is a skill published in the GitHub repository Detective-XH/DocGraph (8 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 827 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
okf-loom
Load this repo skill when working with Open Knowledge Format (OKF) bundles: validate, search, discover, update, render, serve the live studio, author concepts, or use the bundled OKF docs. The repo is the distribution unit; run scripts from the checkout with scripts/okf-loom.
redact-pii
Redact personal data from a document through the connected Superlinked MCP edge before working with the content. Use when the user asks to redact, anonymize, scrub, de-identify, or remove PII/sensitive data from a document.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
pdf-processing
Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
legal-writer
Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification…