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-katanagit 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-katana)<a href="https://agentmods.dev/skills/bop-clocktower/canary/canary-katana"><img src="https://agentmods.dev/badge/skills/bop-clocktower/canary/canary-katana/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-katana"><img src="https://agentmods.dev/badge/skills/bop-clocktower/canary/canary-katana.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 | $0.00094 | $0.02636 |
| Opus 5 | $0.00047 | $0.01318 |
| Sonnet 5 | $0.00019 | $0.00527 |
| Haiku 4.5 | $0.00009 | $0.00264 |
Grade A, and why
canary-katana 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canary Katana
Named for Tatsu Yamashiro's Soultaker — the blade that captures the soul of whatever it cuts. A deleted test is coverage that leaves without a trace: the suite still goes green, the gap is invisible, and nobody notices until the bug it caught ships. Katana catches every test as it is removed or muted, records who took it and why, and raises its voice only when the cut was the last thing guarding a critical path.
Tier-0 deterministic analysis: no LLM, no network, no secrets, no dependency on any other skill at runtime.
What it captures
| Event | Detected from a diff |
|---|---|
removed |
a def test_* / async def test_* (Python) or describe/it/test('…') (JS/TS) that left on a - line and did not come back on the + side |
skipped |
a +-side skip/mute marker: @pytest.mark.skip / skipif / xfail, or it.skip / test.skip / describe.skip, it.only / test.only, xit / xdescribe / fit |
A test flipped in place from it('x') to it.skip('x') is one event, not
two: the skip supersedes the removal so the ledger never double-counts a
mute-in-place as both a deletion and a skip.
The general form of that rule is the emphasis above: a (file, title) that
reappears on the + side was modified, not removed. Without it, any rewrite
of a declaration line recorded a deletion of a test that is still in the tree —
a prettier reflow of a long signature, or a .skip lifted in place, was enough
(#783). The ledger is append-only, so such a row is permanent and cannot be
corrected without the hand-edit the ledger exists to prevent; and a consumer
that attributes on the newest matching row would hand every test under a phantom
removal of a describe the wrong ticket. A rename is still a removal — the
old title's coverage really is gone.
What ships with it
4 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.
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 Changed · +71 lines 0e5dd3ffbc6f
- 10d ago First seen · 173 lines · 94 tokens per session scan A 8f256197cc9f
canary-katana is a skill published in the GitHub repository bop-clocktower/canary (4 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 2,636 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 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.