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 docgraph-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/docgraph-drift-audit)<a href="https://agentmods.dev/skills/detective-xh/docgraph/docgraph-drift-audit"><img src="https://agentmods.dev/badge/skills/detective-xh/docgraph/docgraph-drift-audit.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.01045 |
| Opus 5 | $0.00020 | $0.00522 |
| Sonnet 5 | $0.00008 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
docgraph-drift-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DocGraph Drift Audit
Invocation — Claude Code:
Skill("docgraph-drift-audit")| OpenCode / Codex: use triggers above.
Scans all indexed .md files and reports how well they conform to DocGraph conventions. Run after bulk content changes, after adding new docs, or when graph queries return unexpected results.
Execution
- Model: Haiku (scan) or Sonnet (fix suggestions)
- Effort: Low-Medium
- Advisor: Not required
Step 1: Get index state
docgraph_status
Record file count, node count, edge count, unresolved refs count. If unresolved refs > 5% of total edges, expect widespread broken-link findings below.
Locate the database and verify sqlite3 is available:
DB=$(find . -name "docgraph.db" -path "*/.docgraph/*" | head -1)
echo "DB: $DB"
command -v sqlite3 >/dev/null 2>&1 || echo "WARNING: sqlite3 not found — install with: brew install sqlite (macOS) or apt install sqlite3 (Linux). Steps 2a–2e require it."
Step 2: Scan drift categories
2a. No frontmatter
sqlite3 "$DB" "SELECT path FROM files WHERE has_frontmatter = 0 ORDER BY path"
PASS if count = 0 for ADR/plan/governance docs. Priority: HIGH for structured docs. LOW for README/changelog.
2b. No outgoing links — isolated docs
sqlite3 "$DB" "
SELECT f.path FROM files f
WHERE NOT EXISTS (
SELECT 1 FROM nodes n
JOIN edges e ON e.source = n.id
WHERE n.file_path = f.path
AND e.kind IN ('references','wikilinks_to','related_to')
)
ORDER BY f.path"
PASS if key docs have at least one outgoing link. Priority: HIGH if doc should relate to others. LOW for standalone entries.
2c. Broken links — unresolved refs
sqlite3 "$DB" "
SELECT reference_text, reference_kind, COUNT(*) as cnt
FROM unresolved_refs
GROUP BY reference_text, reference_kind
ORDER BY cnt DESC LIMIT 20"
PASS if count = 0. Broken links are graph bugs — HIGH priority always.
2d. No headings
sqlite3 "$DB" "
SELECT f.path FROM files f
LEFT JOIN nodes n ON n.file_path = f.path AND n.kind = 'heading'
WHERE n.id IS NULL ORDER BY f.path"
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.
- 6d ago First seen · 146 lines · 40 tokens per session scan A 87c2b6d18a24
docgraph-drift-audit is a skill published in the GitHub repository Detective-XH/DocGraph (8 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,045 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
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
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.
document-as-you-go
Quando você termina uma tarefa/commit, pague a dívida de documentação da wiki antes de fechar. Use este skill no Claude Code, OpenCode, Codex CLI ou qualquer agente que tenha a skill MCP do livewiki.
bootstrap-wiki
Bootstrap a repository's initial livewiki documentation through MCP when no wiki pages exist or the user explicitly asks for its first full wiki. Use for deliberate, long-running initial documentation.
context-atlas
Retrieve and interpret durable, evidence-backed project memory from Context Atlas, including overviews, architecture, chronology, decisions, risks, provenance, health, and task-specific context packs. Use when Codex must onboard to an unfamiliar repository, explain how or why code evolved, prepare context before a…
firecrawl-build-scrape
Integrate Firecrawl /scrape into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.