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 laurigates/claude-plugins --skill execution-grounded-reviewgit clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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/laurigates/claude-plugins/execution-grounded-review)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/execution-grounded-review"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/execution-grounded-review/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/laurigates/claude-plugins/execution-grounded-review"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/execution-grounded-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 7 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium MCP Rug Pull · line 76 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 76 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 76 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00030 | $0.05308 |
| Opus 5.5 | $0.00012 | $0.02123 |
| Sonnet 5.5 | $0.00006 | $0.01062 |
| Haiku 4.5 | $0.00003 | $0.00531 |
Grade A, and why
execution-grounded-review 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 18d 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execution-Grounded Review
A normal review reads the diff and asks "does this look right?" — and an
implementation can look complete while a criterion silently fails. This skill
refuses to grade an implementation on appearance: it runs the suite first,
then traces each acceptance criterion to execution evidence — a test that
actually exercised it, or observed behaviour — and marks anything it cannot
back with execution as UNVERIFIED rather than passing it on faith.
It is the execution-grounded verifier in the agent-patterns review family:
where adversarial-review attacks a design for faults and cold-read-gate
measures whether text survives a reader, this skill verifies that running
code meets its stated acceptance criteria. It is the reusable independent
verifier a judgement-based loop gate delegates to (.claude/rules/loop-integrity.md, Pillar 1).
When to Use This Skill
| Use this skill when... | Use something else instead when... |
|---|---|
| Verifying an implementation meets explicit acceptance criteria, proven by running it | First-pass review of a diff → code-quality-plugin:code-review |
Gating a loop/phase done on an independent check of behaviour |
Red-teaming a design or ADR for faults → agent-patterns-plugin:adversarial-review |
| Confirming a fix actually fixes the reported failure (not just compiles) | Checking premises/facts before work starts → agent-patterns-plugin:verify-before-plan |
| Closing the loop on "is every requirement actually covered by a test?" | Legibility of outward text → agent-patterns-plugin:cold-read-gate |
The Stance
| Move | What it means |
|---|---|
| Execute first | Run the full suite + typecheck + lint before any verdict. A criterion is PASS only with execution evidence — never "the code looks like it does this". |
| Trace each criterion | One ledger row per acceptance criterion: premise → evidence (file:line / test name / observed output) → verdict. |
| No silent pass | A criterion with no execution backing is UNVERIFIED (a coverage gap to surface), not an assumed pass. |
| Flaws before the verdict | The report states its narrative-changing limitations — gaps and caveats that would flip or weaken the verdict — ahead of the verdict, and says none explicitly when there are none (Step 5). |
| Match the production sequence | For a round-trip / determinism / reproducibility / idempotence claim, a passing test is evidence only if its operation sequence reproduces the real production call path — not a convenient shorter one (see Step 3a). |
| Intent-starved verifier | The isolated verifier reads the criteria, the diff, and the captured execution evidence — not the author's plan narrative or rationale, which would let it rationalise a pass. |
| Bounded loop | One revise round on fail; a third means a structural problem the gate can't resolve. |
What ships with it
3 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.
- 18d ago Changed · -10 lines 48a68ce7a71c
- 24d ago Changed · +88 lines ef3dd602e39a
- 1mo ago Changed · +44 lines fc46658fca8b
- 1mo ago Changed · +1 lines 5749b5c283dd
- 1mo ago First seen · 264 lines · 30 tokens per session scan A 468de8dc0dc2
execution-grounded-review is a skill published in the GitHub repository laurigates/claude-plugins (59 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 5,308 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
phpunit-test-team-reviewing
Use this skill when the user asks for a team-based, consensus, multi-reviewer, or red-team review of Shopware PHPUnit tests — trigger phrases like "team review these tests", "consensus review the tests in PR.
phpunit-test-reconciling
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.
pr-feedback
Works through review comments and failing CI on an open pull request, triaging each comment, fixing with tests, replying on every thread, and looping until CI is green. Use when asked to address review comments, fix CI, or handle PR feedback.
verify-acceptance
Runs the acceptance-verifier agent to map a diff against acceptance criteria and returns a PASS/FAIL/PARTIAL/UNTESTED matrix as JSON. Use for CI or headless runs, for example claude -p "/agents-virtuoso:verify-acceptance 123 origin/main".
continuous-improvement
Orchestrate a continuous improvement cycle: spawn live-tester for live testing, researcher for dependency monitoring and research, arch-analyst for code quality and architecture review, and security-analyst for vulnerability scanning. Read-only; aggregates findings into a cycle journal. Runs as an agent team when…
specification-compliance-review
Use this skill when an implementation is described as partial, passing, or complete and the task is to determine whether it actually satisfies an explicit specification. This is not a generic code review and not a re-run of the test suite. The central question is: does every normative requirement have both a correct…