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/detective-xh/docgraph/code-doc-drift-auditnpx skills add Detective-XH/DocGraph --skill code-doc-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/code-doc-drift-audit)<a href="https://agentmods.dev/skills/detective-xh/docgraph/code-doc-drift-audit"><img src="https://agentmods.dev/badge/skills/detective-xh/docgraph/code-doc-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 | $0.00062 | $0.00948 |
| Opus 5 | $0.00031 | $0.00474 |
| Sonnet 5 | $0.00012 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
code-doc-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 4d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs-Code Drift Audit
Invocation — Claude Code:
Skill("code-doc-drift-audit")| OpenCode / Codex: use triggers above.
Runs the DocGraph docs-code 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 prerequisites
docgraph_status
Confirm:
code_docpack is listed under Domain Packs and is enabled- At least one
code_filenode is indexed (check node count or rundocgraph_search kind=code_file)
If code_doc is not enabled, tell the user to run:
docgraph pack enable code_doc <project-path>
# or for workspace mode:
docgraph pack enable --workspace code_doc <workspace-path>
Then wait for the sync to complete before proceeding.
Step 2: Run the drift audit
docgraph_context task="docs-code drift audit" format=drift_audit
This calls DocGraph's GetDriftFindings engine, which checks (code_doc findings only):
| Code | Severity | Meaning |
|---|---|---|
code.missing_symbol |
warning | A doc links to a code file path that is not indexed — broken doc-to-code reference |
code.undocumented_export |
info | A code file has no incoming references, wikilinks_to, or related_to edges from any doc — no documentation points to it |
code.unanchored_feature |
info | An approved or review-status doc has no outgoing edge to any indexed code file — feature doc not connected to implementation |
If code_doc is disabled, the output will show zero code.* findings regardless of repo content.
Step 3: Present findings to the user
Group findings by code, severity first (warnings before info).
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
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.
- 4d ago First seen · 113 lines · 62 tokens per session scan A 3f5ccbcb6d5e
code-doc-drift-audit is a skill published in the GitHub repository Detective-XH/DocGraph (7 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 948 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
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.
ingest-l1
L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…
research-l2
Executes Phases 1-3 of the L2 process of the abapwiki knowledge base on a slice: launches the abap-functional-researcher sub-agent (gap discovery + multi-source auto-research: wiki -> raw/docs -> MCP abap-fs on the system read-only -> standard knowledge), ingests gaps and evidence, and generates questionnaires for…
slice-init
Creates an L2 slice in the abapwiki knowledge base: a business process on which to build functional documentation. Writes the manifest (curated anchors + mandatory real owner) and derives the membership from the dependency graph (BFS hop<=2). Use this skill to start the L2 process on a custom domain. Does not promote…
capture-answer
Ingests an expert's answers to an L2 questionnaire in the abapwiki knowledge base: transforms the answers (filled in the interviews/ file or given verbally) into a canonical citable expert-answer (slices/ /inputs/expert-answers/), moves gaps to 'answered' and closes the questions. Use this skill when the owner/expert…
ingest-l0
L0 bootstrap of the abapwiki knowledge base: creates stubs for all custom objects from the TADIR. Use this skill to initialize the repo from scratch or to ingest a new TADIR export. Deterministic operations (no LLM sub-agent), idempotent.