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-critical-areasgit 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-critical-areas)<a href="https://agentmods.dev/skills/bop-clocktower/canary/canary-critical-areas"><img src="https://agentmods.dev/badge/skills/bop-clocktower/canary/canary-critical-areas/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-critical-areas"><img src="https://agentmods.dev/badge/skills/bop-clocktower/canary/canary-critical-areas.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 | $0.00055 | $0.01117 |
| Opus 5 | $0.00028 | $0.00558 |
| Sonnet 5 | $0.00011 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
canary-critical-areas 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canary: Critical Areas
Identifies the highest-risk areas of a codebase so test effort goes where it matters most. Uses multiple signals, degrades gracefully when advanced tooling is unavailable.
When to Use
-
Before writing new tests: "where should I focus?"
-
After a large diff lands: "what did this change put at risk?"
-
As Phase 1 of
/canary-test-pipeline -
When asked to prioritise test coverage
Signals
Collect all available signals, score each area, and rank by composite risk score.
1. Churn / hotspot (always available)
With harness MCP available: call detect_anomalies (metric hotspotScore,
plus its co-change / single-point-of-failure signals). Harness's hotspot score
already blends churn with structural risk, so use it directly as this signal and
skip the raw git log pass. Normalise the returned scores to 0–1.
Fallback (no MCP):
git log --stat --since="90 days ago" -- <path> | grep -c "^"
Files changed most frequently in the last 90 days score higher. Normalise to 0–1 across all files in scope.
2. Downstream dependents
With harness MCP available: call get_impact for each candidate file
(filePath, mode: "summary") and read the affected-node counts it returns
(tests / docs / code grouped by type). This is the purpose-built impact
primitive — do not hand-walk get_relationships edge-by-edge; get_impact
already computes the transitive downstream set. More affected nodes ⇒ higher
score.
Fallback (no MCP): scan for import statements referencing each file using
grep -r. Count unique files that import each candidate.
Files with more inbound dependents score higher — a change here breaks more.
3. Business-critical / critical-path flags
With harness MCP available: call get_critical_paths and add a fixed boost
(+0.3) to any area whose functions appear in the returned perf-critical set.
Also query ask_graph for business_fact nodes associated with each area; any
business-critical annotation adds the same +0.3 boost (apply the boost once,
whichever signal fires).
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.
- 11d ago First seen · 143 lines · 55 tokens per session scan A 1ead98eed65b
canary-critical-areas is a skill published in the GitHub repository bop-clocktower/canary (4 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,117 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.