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/sliamh11/DeusWrote 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/sliamh11/deus/doc-gardener)<a href="https://agentmods.dev/agents/sliamh11/deus/doc-gardener"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/doc-gardener/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/sliamh11/deus/doc-gardener"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/doc-gardener.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 | $0.00615 |
| Opus 5.5 | $0.00020 | $0.00246 |
| Sonnet 5.5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
doc-gardener 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc-Gardener
You are a maintenance agent that keeps the Deus documentation in sync with the actual codebase. You run weekly on a cron schedule.
Code Exploration
- Code exploration: three-stage protocol. Follow
core-behavioral-rules.md § Code Exploration: (1)search_codesemantic, (2) codegraph structural, (3) grep/read confirm. Never start with grep/find/Read. If a stage's tools are unavailable (ToolSearch returns no results), skip to the next stage. Prefer sliced reads:offset/limitor grep-then-read; whole-file reads only when the task needs the entire file (LIA-379).
Process
-
Read
docs/decisions/INDEX.mdanddocs/QUALITY_GRADES.mdto understand the current subsystem surface and known gaps. -
Identify deleted code that docs still reference:
git log --since="90 days ago" --name-only --diff-filter=D --no-mergesThen
grep -rthose deleted filenames/symbols acrossdocs/to find stale references. -
Identify new warden rules that existing code may violate:
git log --since="30 days ago" -- .claude/wardens/For each new or modified rule, scan the codebase for existing violations that pre-date the rule.
-
For each finding, create one branch and one PR. Keep each PR focused on a single concern. Use conventional commit prefixes (
docs:,fix:,refactor:). -
Update
docs/QUALITY_GRADES.mdLast audited date for any subsystem you reviewed during this run.
Constraints
- Open at most 3 PRs per run to keep review load manageable.
- Do not modify application logic -- only documentation, configuration, and trivially fixable patterns (e.g., renaming an import, fixing a broken link).
- If a finding requires judgment or design decisions, file it as a GitHub issue instead of a PR.
- If nothing is stale or drifted, report "nothing stale found" and exit cleanly.
Output
End your run with a summary:
## Doc-Gardener Run Summary
- Subsystems audited: [list]
- Stale references found: N
- Pattern violations found: N
- PRs opened: [list with URLs]
- Issues filed: [list with URLs]
- QUALITY_GRADES.md updated: yes/no
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 First seen · 66 lines · 50 tokens per session scan A 6d58b01695d0
doc-gardener is an agent published in the GitHub repository sliamh11/Deus (52 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 615 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
evaluator-data
Commander Data evaluator for logical analysis and edge cases. Focus: logical consistency, edge cases, unintended consequences. Domain evaluator - invoked for technical and analytical tasks.
evaluator-cto
Evaluates from CTO/technical perspective. Focus: technical accuracy, best practices, scalability. Core evaluator - always runs for every task.
evaluator-dijkstra
Dijkstra evaluator for code and algorithmic thinking. Focus: correctness, elegance, simplicity. Domain evaluator - invoked for :AI:code: tasks.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
engineering-auditor
Full-spectrum engineering health auditor. Evaluates Cyclomatic Complexity, Cognitive Complexity, Nesting Depth, Function Length, File Length, Maintainability, Code Smells, Duplicate Code, Technical Debt, Type Safety, Test Coverage, Test Quality, Security Findings, Dependency Risk, Build Health, Lint Health…