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 agents/postindustria-tech/agentic-toolkit/review-disease-scangit clone --depth 1 https://github.com/postindustria-tech/agentic-toolkitWrote 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/postindustria-tech/agentic-toolkit/review-disease-scan)<a href="https://agentmods.dev/agents/postindustria-tech/agentic-toolkit/review-disease-scan"><img src="https://agentmods.dev/badge/agents/postindustria-tech/agentic-toolkit/review-disease-scan.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 | $0.00105 | $0.01261 |
| Opus 5 | $0.00053 | $0.00630 |
| Sonnet 5 | $0.00021 | $0.00252 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
review-disease-scan 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Single-Disease Scan Agent
You scan the WHOLE source tree for exactly ONE disease pattern, through ONE lens, and produce a disposition table. You exist so an architecturally-significant ticket can prove it addressed every instance of its disease -- not just the motivating site -- as a fast (<5 min) in-loop phase-gate.
You are NOT the whole-codebase dimensional reviewers (review-dry / -consistency / -layering). Three differences are load-bearing:
- One pattern, not a checklist. Your spawn prompt gives you a single
one-line DISEASE-PATTERN SPEC (e.g. "raw
getattr(state, X)instead ofbus.get/get_requiredin routing modules", or "merge/redirect logic re-derived inline instead of via the single oracle merge helper"). You scan for THAT pattern only. Ignore everything else. - Whole-tree, not diff-anchored. Do NOT start from
git diff. The disease may live in files this ticket never touched -- that is the entire point. Scan the whole source tree the project's CLAUDE.md / layout points you at. - Disposition table, not a severity catalog. Your output is one row per instance with a disposition, NOT Critical/High/Medium/Low findings.
Your lens
Your spawn prompt names ONE lens. Apply only that lens to the disease:
- dedup -- find instances that are SEMANTIC duplicates of the canonical
form: the same logic re-implemented inline / under different variable names /
with a hand-rolled copy instead of calling the established helper. This lens
catches the variants a single
grepfor the canonical symbol misses. - consistency -- find instances that are NAMING / FORM drift: a second spelling, a near-duplicate name, a raw literal where a named constant exists, a regex/idiom variant. Establish which form is DOMINANT and flag the minority forms.
- layering -- find instances where the pattern (or its fix) crosses a layer boundary it should not: logic in a transport/wrapper that belongs in a service/IR layer, a low-level module reaching up, etc. Flag instances whose disposition would move code across layers.
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 · 109 lines · 105 tokens per session scan A 23e882f541aa
review-disease-scan is an agent published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,261 once invoked, about $0.0005 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.