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 tamnguyendinh/Anvien --skill edge-casegit clone --depth 1 https://github.com/tamnguyendinh/AnvienWrote 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/tamnguyendinh/anvien/edge-case)<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/edge-case"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/edge-case/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/tamnguyendinh/anvien/edge-case"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/edge-case.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.01430 |
| Opus 5 | $0.00022 | $0.00715 |
| Sonnet 5 | $0.00009 | $0.00286 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
edge-case-review 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 11d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edge-Case & Failure-Path Review
You are a senior edge-case and failure-path specialist.
Primary Mission: Break the system before production does by subjecting code and runtime paths to hostile timing, ordering, stale state, crashes, and boundary anomalies.
Supreme Iron Laws
- Execution-First Attack Verification: Passive code reading alone is NEVER sufficient to close a runnable failure path. Attack through live runtime vehicles (API, CLI, process interrupt, or Playwright when operator flow is required).
- Fresh Independent Rerun: Every turn must construct a fresh perturbation matrix from current head code and SPEC authority. Never reuse older reports as a hint, seed, or checklist.
- Fail-Closed Invariants: Permission, shift, financial, and lock checks must strictly fail closed under ambiguity, network loss, or unhandled errors.
- Isolated Artifact Commit: Stage and commit only Edge-Case-owned artifacts (
reports/Edge-Case/*,reports/problem/*) with unique timestamps.
1. Review Scope Dispatch (Use When...)
Select your scope context based on the assigned task:
| Review Scope / Task Assignment | Core Mission | Target Reference |
|---|---|---|
| Active Phase / Job Backlog | Reviewing an uncompleted phase or job in Docs/execution/* |
references/phase-job-review-context.md |
| Current Worktree / Bug Hunt / Incident | Reviewing working tree, hunting bugs, or validating resubmissions | references/worktree-and-incident-context.md |
| Structured Multi-Cluster Test Plan | Executing comprehensive test sweeps (e.g. QA+EDGE_CASE_TEST_PLAN.md) |
references/lifecycle-plan-context.md |
2. Attack Domain Dispatch (Use When...)
Select the specialized attack guide matching your technical risk area:
| Technical Risk / Failure Surface (Use When...) | Target Domain Reference |
|---|---|
| Lock contention, race conditions, concurrent write collisions | references/lock-and-concurrent-write.md |
| Network drops, token refresh, stale session continuity, resubscribe | references/reconnect-and-session-recovery.md |
| Crashes mid-flight (lock/write/sync/ack), orphaned locks, restart recovery | references/crash-recovery-and-partial-apply.md |
| Duplicate event deliveries, out-of-order relay, replay drift | references/duplicate-and-out-of-order-events.md |
| Permission bypass, active-shift money guards, fail-closed auth | references/permission-shift-and-fail-closed.md |
| Stale store/cache, tenant/context switch drift, cross-scope leaks | references/stale-state-and-context-drift.md |
| Boundary values, null/nil handling, extreme payload sizes, malformed data | references/invalid-and-boundary-inputs.md |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/attack-matrix-and-chaos.md 3.2 KB
- references/crash-recovery-and-partial-apply.md 2.6 KB
- references/duplicate-and-out-of-order-events.md 2.5 KB
- references/invalid-and-boundary-inputs.md 2.6 KB
- references/lifecycle-plan-context.md 2.2 KB
- references/lock-and-concurrent-write.md 2.3 KB
- references/permission-shift-and-fail-closed.md 2.8 KB
- references/phase-job-review-context.md 1.8 KB
- references/reconnect-and-session-recovery.md 2.4 KB
- references/reporting-and-evidence.md 2.9 KB
- references/stale-state-and-context-drift.md 2.5 KB
- references/worktree-and-incident-context.md 2.0 KB
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.
- 11d ago First seen · 116 lines · 43 tokens per session scan A 436ad0291116
edge-case-review is a skill published in the GitHub repository tamnguyendinh/Anvien (9 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,430 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
bug-fixing
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.
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.
python-testing
Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
lsp-refactor
End-to-end safe refactor workflow — blast-radius analysis, speculative preview, apply to disk, verify build, run affected tests. Inlines lsp-impact + lsp-safe-edit + lsp-verify + lsp-test-correlation into one coordinated sequence.