Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

check — drift report — measured AI agent skill | DecimalAI

juliusbrussee/check

SkillScore58Maintained

Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec. Phrasings: "check drift", "audit the spec", "does the code still match §V", "check invariants", "spec vs code".

Code Reviewby juliusbrussee

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

QA & Test Engineering pack

decimalai skills pull juliusbrussee-check

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/juliusbrussee-check/SKILL.md

Raw file: /s/juliusbrussee-check/SKILL.md ↗ · machine-readable summary at /s/juliusbrussee-check.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

24 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—+9% tokens0% turns58% of whole cases pass with skill (14/24)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-24	✗→✓	▲ Improved	-7%	0%
case-11	✗→✓	▲ Improved	-10%	0%
case-13	✗→✓	▲ Improved	-1%	0%
case-14	✗→✓	▲ Improved	-4%	0%
case-15	✗→✓	▲ Improved	-15%	0%

Showing 5 of 24 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

juliusbrussee / cavekit

skills/check/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

check — drift report

Pure diagnostic. Reports violations. Writes nothing. User decides remedy.

Spec drifting silently from code is the #1 SDD failure mode. check is the detector. Run it after each /build and before each ship — drift caught here is a diff; drift caught in prod is a §B.

LOAD

Read SPEC.md. If missing → "no spec, nothing to check." Stop.
Parse invocation args:

§V → check invariants only (default)
§I → check interfaces
§T → audit task status vs code
--all → all three

CHECK §V — invariants

For each V<n>:

Translate invariant into verifiable claim about code.
Grep / read relevant files.
Classify: HOLD / VIOLATE / UNVERIFIABLE.
Record address + file:line evidence.

CHECK §I — interfaces

For each I item:

Locate implementation.
Classify:

MATCH — shape in code = shape in spec.
DRIFT — impl exists, shape differs.
MISSING — impl absent.
EXTRA — code exposes surface not in §I.

CHECK §T — tasks

For each T<n>:

If x: verify claimed work present.
If ~: note as in-progress.
If .: note as pending.
Flag x rows with no evidence as STALE.

REPORT

Caveman. Grouped by severity.

## §V drift
V2 VIOLATE: auth/mw.go:47 uses `<` not `≤`. see §B.1.
V5 UNVERIFIABLE: no test covers ∀ req path.

## §I drift
I.api DRIFT: POST /x returns `{result}` not `{id}`. route.go:112.
I.cmd MISSING: `foo bar` absent from cli/*.go.

## §T drift
T3 STALE: status `x`, no middleware file exists.

## summary
2 violate. 1 missing. 1 stale. 1 unverifiable.
next: spec skill with `bug:` or fix code at cited lines.

REMEDY HINTS (not actions)

End report with one-line hint per class:

VIOLATE / DRIFT → invoke spec skill bug: <V.n> or fix code.
MISSING → invoke build skill on §T.n if task exists; else spec skill amend §T.
STALE → spec skill amend §T to uncheck.
EXTRA → spec skill amend §I to document, or delete code.

Never invoke fixes. Report only.

NON-GOALS

Zero writes. No SPEC.md edits. No code edits.
No sub-agents. Main thread reads.
No scores, no grades. Binary per item: holds or drifts.

Want to see if juliusbrussee/check would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.