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 zookanalytics/gc-toolkit --skill review-correctnessgit clone --depth 1 https://github.com/zookanalytics/gc-toolkitWrote 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/zookanalytics/gc-toolkit/review-correctness)<a href="https://agentmods.dev/skills/zookanalytics/gc-toolkit/review-correctness"><img src="https://agentmods.dev/badge/skills/zookanalytics/gc-toolkit/review-correctness/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/zookanalytics/gc-toolkit/review-correctness"><img src="https://agentmods.dev/badge/skills/zookanalytics/gc-toolkit/review-correctness.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 | $0.00090 | $0.02374 |
| Opus 5.5 | $0.00036 | $0.00950 |
| Sonnet 5.5 | $0.00018 | $0.00475 |
| Haiku 4.5 | $0.00009 | $0.00237 |
Grade A, and why
review-correctness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The correctness check
The correctness check is the standing review of whether a change is correct and safe as merged. It is the concern, not a tool: no reviewer is presumed.
The review formula is the frame you work in. It pins the commit, makes the
review workspace and the hb keepalive, and carries the verdict envelope and
the one signoff.sh call. This file is what the correctness check reads, runs
and judges inside that frame. Run each block below in a shell that has first
run the formula's pin, keepalive and workspace blocks, so the pins,
REVIEW_WT and hb are set.
Read the whole diff
Read the whole diff the formula pins, origin/$BASE...$REVIEWED_OID. A large
diff gets read in chunks, not sampled.
Settle the test evidence
The self-review that built a commit runs the rig's declared test command and
stamps the head it saw pass on the work bead as self_review_passed_sha. The
anchor's stamp is evidence only when it is the reviewed commit's full sha and
the rig declares a test command. A merge of the base or a rework round leaves
it naming an older head, and where the rig declares no test command the stamp
certifies no declared tests:
# >>> review-test-evidence
ANCHOR=$(printf '%s' "$M" | jq -r '.anchor_bead // empty')
STAMP=""
[ -n "$ANCHOR" ] && STAMP=$(gc bd show "$ANCHOR" --json 2>/dev/null | jq -r '.[0].metadata.self_review_passed_sha // empty' 2>/dev/null)
DECLARED=$(gc formula show mol-polecat-work ${GC_RIG:+--rig="$GC_RIG"} --json 2>/dev/null | jq -r '[.vars[]? | select(.name == "affected_tests_command" or .name == "test_command") | if .rig_default != null then .rig_default else (.default // "") end | select(. != "")] | length' 2>/dev/null)
if [ -n "$STAMP" ] && [ "$STAMP" = "$REVIEWED_OID" ] && [ "${DECLARED:-0}" -gt 0 ] 2>/dev/null; then
echo "test evidence: the anchor's self-review passed the rig's declared tests at $REVIEWED_OID; run no suite"
else
echo "no test evidence at ${REVIEWED_OID:-an unpinned commit} (anchor stamp: ${STAMP:-none}; declared test commands: ${DECLARED:-unread}); run the suites the diff touches"
fi
# <<< review-test-evidence
What ships with it
6 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.
- today First seen · 159 lines · 90 tokens per session scan A 779cbfebccce
review-correctness is a skill published in the GitHub repository zookanalytics/gc-toolkit (5 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 2,374 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
attest
Verifying spec compliance: extracts ACs from specs, adversarially checks conformance, generates BDD scenarios and traceability matrices. Use when impl must be proven to match a PRD/SRS/AC.
test-strategy
Coverage-design method for qa-engineer — pyramid ratios per archetype, equivalence/boundary/property case selection, mutation score as the real coverage signal, and a flake-quarantine policy. Turns "coverage is 90%" (a number with no method) into a defensible test plan. Emits TEST-STRATEGY-{slug}.md, which the QA gate…
quant-validation
The methods a financial-ML result has to survive before it is evidence — purged cross-validation with an embargo, triple-barrier labelling, sample uniqueness under overlapping labels, fractional differentiation, meta-labelling, and multiple-testing correction. Written because the invariants were required of…
adversarial-implementation-review-coach
Adversarial implementation review based on Block's g3 dialectical autocoding research. Use when validating implementation completeness against requirements with fresh objectivity.
cdt
Multi-agent development workflow using Agent Teams. Supports five modes: plan (architect teammate + PM teammate debate → plan.md), dev (developer teammate + code-tester teammate + qa-tester teammate + reviewer teammate iterate → code), full (plan → approval gate → dev), auto (plan → dev, no gate), and bugfix (tester +…