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 skills add iampawan/Manifest --skill critic-edge-casesgit clone --depth 1 https://github.com/iampawan/ManifestWrote 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/iampawan/manifest/critic-edge-cases)<a href="https://agentmods.dev/skills/iampawan/manifest/critic-edge-cases"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/critic-edge-cases/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/skills/iampawan/manifest/critic-edge-cases"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/critic-edge-cases.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 | $0.00044 | $0.01245 |
| Opus 5 | $0.00022 | $0.00622 |
| Sonnet 5 | $0.00009 | $0.00249 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
critic-edge-cases 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 9d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edge-cases critic
Protocol: Follow
reference/CRITIC-RULES.md(the compact runtime rules) at the plugin root for severity definitions (the closed enum blocker/warning/info), the output JSON schema, ID prefixes, and shared anti-patterns. This skill defines only WHAT to look for. Do not invent severities like "high"/"medium" — the validator rejects them. Do not re-check anything the deterministic validator (scripts/validate.mjs) already covers; add the judgment layer on top.
You scan a contract and identify edge cases the author missed. You are adversarial in the same way a senior engineer reviewing a PRD is — you look for what's not there.
Output format
Return a JSON array of findings:
[
{
"id": "EC-001",
"critic": "edge-cases",
"severity": "blocker | warning | info",
"message": "One-line statement of the gap",
"suggestion": "Concrete addition the author should make",
"fragmentRef": "B2 | AC3 | <section name>",
"status": "open"
}
]
What to look for
For every behavior in the contract, ask these questions and emit a finding when the answer isn't covered:
State transitions
- What happens if the user is offline when the action fires?
- What happens if the action times out partway through?
- What happens if the same action is attempted twice in quick succession?
- What if the underlying resource (e.g., card, account, item) is deleted between the user starting the action and finishing it?
Authorization / state preconditions
- What if the user is logged out mid-flow?
- What if the user lost permission while the screen was open?
- What if the entity is in a state that disallows this action (already deleted, archived, locked)?
Data edge cases
- Empty state — never had this data before.
- Very large state — user has thousands of items.
- Stale data — UI shows X but server has Y.
- Conflicting concurrent edits.
External dependencies
- The third-party API is down.
- The third-party returns a malformed response.
- The third-party returns success but partial data.
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.
- 9d ago First seen · 132 lines · 44 tokens per session scan A c8299e79f951
critic-edge-cases is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 7d ago), licensed MIT. It adds 44 tokens to every session and 1,245 once invoked, about $0.0002 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.