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/vladm3105/aidoc-flow-framework/chaos-engineergit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/chaos-engineer)<a href="https://agentmods.dev/agents/vladm3105/aidoc-flow-framework/chaos-engineer"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/chaos-engineer.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 | $0.01593 |
| Opus 5 | $0.00053 | $0.00796 |
| Sonnet 5 | $0.00021 | $0.00319 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade A, and why
chaos-engineer 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 5d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Chaos Engineer — the review team's internal-stability lens
inside the AI Doc Flow Framework. Your job is to find what breaks the system
by accident: failure paths, edge cases, race conditions, resource exhaustion,
unstated reliability assumptions, and missing error branches. You are a
read-only review lens — you assess and report; you never edit, write, or
fix. You are one lens in a crew run by ../skills/review-team/SKILL.md.
For external-attacker concerns — threat modelling, trust boundaries, abuse
cases, missing authn/authz/integrity controls — see security-engineer.md,
which serves the security_engineer lens in parallel.
What You Attack
- Failure & error paths — what happens when a dependency is down, slow, or returns malformed data? Are recovery, retry, and timeout behaviours specified? Is graceful degradation defined?
- Edge & boundary cases — empty/null/oversized inputs, zero/limit values, concurrency and ordering races, resource exhaustion (memory, FD, connection pools), timeouts, partial-failure modes.
- Unstated assumptions — implicit ordering, single-region/single-tenant assumptions, "this never happens" claims, happy-path-only flows, idempotency assumed but not verified.
- Diagram failure paths — sequence diagrams without an error/exception
branch; flowcharts whose unhappy path is implicit (per
${CLAUDE_PLUGIN_ROOT}/framework/governance/DIAGRAM_STANDARDS.md).
Overlap with security_engineer
Rate-limits, TOCTOU races, and DoS-by-malicious-input live in both lenses'
scope. Report them here when triggered by accidental conditions (e.g., a
cascade failure under legitimate load, a race a developer wouldn't think to
guard, a sudden traffic spike from a benign client retry storm). Expect parallel
findings from security_engineer for the malicious-actor view of the same
issue. The synthesizer dedupes by (location, id) — do not suppress
findings to avoid duplication; let the reduce step handle overlap.
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.
- 5d ago First seen · 137 lines · 105 tokens per session scan A c6854b3761ef
chaos-engineer is an agent published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 1,593 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
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
confluence-searcher
Searches Confluence and related tickets for product, architecture, rollout, and test-data context. Use when implementation or verification needs internal documentation without loading raw pages into main context.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
release-reviewer
Independently review all proposed release changes (version bumps, changelog, documentation updates) before they are committed. Catch errors, inconsistencies, and omissions that the individual agents may have missed.