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 bop-clocktower/canary --skill canary-edge-case-discoverygit clone --depth 1 https://github.com/bop-clocktower/canaryWrote 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/bop-clocktower/canary/canary-edge-case-discovery)<a href="https://agentmods.dev/skills/bop-clocktower/canary/canary-edge-case-discovery"><img src="https://agentmods.dev/badge/skills/bop-clocktower/canary/canary-edge-case-discovery/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/bop-clocktower/canary/canary-edge-case-discovery"><img src="https://agentmods.dev/badge/skills/bop-clocktower/canary/canary-edge-case-discovery.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 | $0.00051 | $0.01347 |
| Opus 5 | $0.00026 | $0.00674 |
| Sonnet 5 | $0.00010 | $0.00269 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
canary-edge-case-discovery 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 12d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canary: Edge Case Discovery
Surfaces the edge cases that tests typically miss: the inputs and conditions that work in demos but break in production.
When to Use
-
After writing happy-path tests: "what else should I test?"
-
When reviewing a feature for robustness
-
As Phase 2 of
/canary-test-pipeline -
When asked "what edge cases should I cover?"
Input
Provide one of:
-
A feature description:
"points accrual on tier upgrade" -
A function signature:
accruePoints(memberId: string, amount: number): Promise<Result> -
A test file path:
tests/loyalty/points.spec.ts -
Or nothing — Canary will infer from open files and recent context
If .canary/critical-areas.json is present, focus edge case discovery on the
highest-risk areas first (rank_score ≥ 0.6).
The Six Categories
For each category, generate specific, actionable cases — not generic advice.
1. Boundary values
Zero, negative, max integer, empty string, null, undefined, one-off-by-one. For amounts: 0, 1, MAX_SAFE_INTEGER, -1, 0.001 (floating point). For strings: empty string, whitespace-only, max-length + 1 character.
2. Race conditions
Concurrent writes to the same resource. Double-submit (user clicks twice). Stale reads after an update. Lock contention. Out-of-order async responses.
3. Locale and timezone
DST transition times. Dates at midnight UTC vs local time. Non-ASCII characters in names and addresses. RTL text in string fields. Locale-specific number formats (1.000,00 vs 1,000.00). Emoji in text fields.
4. Partial network
Request timeout mid-flight. Dropped connection after partial response. Retry storms (client retries while server is still processing). Response truncation.
5. Unexpected input shapes
Extra fields the schema doesn't expect. Missing required fields. Wrong types (string where number expected). SQL or script injection strings. Deeply nested objects. Arrays where scalars expected.
6. Accessibility
Keyboard-only navigation paths. Missing ARIA labels. Focus trap conditions. Screen reader text for dynamic content. Colour contrast for status indicators. (Only include if the input is a UI feature or test.)
What ships with it
1 file 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.
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.
- 12d ago First seen · 161 lines · 51 tokens per session scan A d17596a4ad17
canary-edge-case-discovery is a skill published in the GitHub repository bop-clocktower/canary (4 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,347 once invoked, about $0.0003 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.