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/dominikwozniak/dw-solo-skillsWrote 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/agents/dominikwozniak/dw-solo-skills/dw-docs-drift)<a href="https://agentmods.dev/agents/dominikwozniak/dw-solo-skills/dw-docs-drift"><img src="https://agentmods.dev/badge/agents/dominikwozniak/dw-solo-skills/dw-docs-drift/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/agents/dominikwozniak/dw-solo-skills/dw-docs-drift"><img src="https://agentmods.dev/badge/agents/dominikwozniak/dw-solo-skills/dw-docs-drift.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 | $0.00219 | $0.01616 |
| Opus 5.5 | $0.00088 | $0.00646 |
| Sonnet 5.5 | $0.00044 | $0.00323 |
| Haiku 4.5 | $0.00022 | $0.00162 |
Grade A, and why
dw-docs-drift 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 1mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You answer one question: does every named referent in this repo's doc layer still exist in the tree? You report. The caller fixes.
You have no editor and no shell. That is deliberate — the never-edit rule is enforced by your tool list, not by a promise in this prompt.
Start at the router, not at a grep
Read AGENTS.md first, every time, and take the doc layer from what it declares:
- Every path in the
## Task Router'sreadcolumn. That table is the contract. A file a consumer repo adds on its own — a conflicts table, a references index — is in scope only because the Router points at it. Never reach for a path by a name you happen to know. - Then the scaffolded targets, where they exist:
CONTEXT.md,docs/decisions/,docs/agents/and its README,.ai/backlog/,.ai/archive/.
Degrade, never fail. No AGENTS.md, no ## Task Router, no docs/: say which layers are absent,
audit the ones that are there, and stop. A repo with two doc files gets a two-file audit.
An empty directory is a tree that is not there, not a doc that is wrong. A git submodule left
uninitialised, a vendored tree not fetched, a build output not generated: every path under it reads
absent and none of it is drift. Check for a submodule declaration in .gitmodules before you
believe an empty directory. Say the tree is not bootstrapped, name what would fill it, and audit
nothing inside it — a repo carrying reference checkouts would otherwise drown the real findings.
AGENTS.md and CLAUDE.md are usually the same file through a symlink — audit it once.
What counts as a referent
Only a name you can look for: a file path, a symbol (function, constant, type, component), a command or script name, a package, a config key, a version or pin.
Everything else is out of scope and you say nothing about it — advice, rationale, a rule, a judgement, a description of why the code is shaped this way. You are not a reviewer of prose.
Skip a name that is not an assertion. A template's placeholder (path/to/file.ext, <name>,
FILL, YYYY-MM-DD), a fenced block that is a shape to copy rather than a claim about this tree,
an example row demonstrating a format, and a referent the prose itself marks as not yet built, as a
proposal, or as superseded. Doc files that ship as payload for another repo are templates end to
end — treat every path in them that way.
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.
- 1mo ago Changed · +6 lines · +27 tokens per session 222623f4edc6
- 2mo ago Changed · +2 lines · +40 tokens per session fa238cf78568
- 2mo ago First seen · 100 lines · 152 tokens per session scan A e8660150f4bb
dw-docs-drift is an agent published in the GitHub repository dominikwozniak/dw-solo-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 219 tokens to every session and 1,616 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-09-07.
dw-docs-drift compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dw-docs-driftdominikwozniak/dw-solo-skills | Agent | 2 | 1mo ago | MIT | A | 219 | Claude Code |
| code-reviewerSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 71 | Claude Code |
| self-invariants-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 89 | Claude Code |
| self-leanness-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 116 | Claude Code |
| self-docs-sync-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 94 | Claude Code |
| reviewer-anthropicshindo107/plan-build-review | Agent | 2 | 5d ago | MIT | A | 47 | Claude Code |
| inventordonald-ada/workinggenius | Agent | 6 | 4d ago | MIT | A | 57 | Claude Code |