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 dimetron/pi-go --skill code-review-pigit clone --depth 1 https://github.com/dimetron/pi-goWrote 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/dimetron/pi-go/code-review-pi)<a href="https://agentmods.dev/skills/dimetron/pi-go/code-review-pi"><img src="https://agentmods.dev/badge/skills/dimetron/pi-go/code-review-pi/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/dimetron/pi-go/code-review-pi"><img src="https://agentmods.dev/badge/skills/dimetron/pi-go/code-review-pi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00895 |
| Opus 5.5 | $0.00020 | $0.00358 |
| Sonnet 5.5 | $0.00010 | $0.00179 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
code-review-pi 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review code for quality, test coverage, and fix problems found.
The canonical output artifact for this skill is ./specs/issues/003-code-review-pi/PROMPT.md.
Only report success after writing the final review summary there.
Steps
-
Identify scope: Run
git diff --name-onlyto find modified files. If there are changes, review only modified packages. If no uncommitted changes, review all packages (./...). -
Run linters: Execute linters on target packages:
go vet ./...golangci-lint run --new-from-rev=HEAD~1 ./...(if available)
-
Run tests and check coverage:
go test -race -count=1 -coverprofile=coverage.out ./...go tool cover -func=coverage.out- Identify failing tests, functions with 0% coverage, packages below 80%
-
Review code quality: Read target files and check for:
- Missing tests for new/changed functions
- Error handling (missing checks, swallowed errors)
- Resource leaks (unclosed files, connections)
- Concurrency issues (race conditions, missing mutexes)
-
Fix issues in parallel using subagents: For each package needing coverage fixes, spawn a subagent to work on it concurrently:
- Use the
agenttool to spawn one subagent per package that needs test coverage improvement - Each subagent prompt: "Write tests for uncovered functions in package . Read the source files, identify untested functions using the coverage data, write table-driven tests covering happy path and error cases. Run
go test -race ./<pkg>/...to verify. NEVER delete existing tests." - While subagents write tests, fix linter warnings and code quality issues yourself
- Wait for all subagents to complete, then verify their work compiles
- Use the
-
Verify gates: All gates must pass before reporting success:
- GATE 1:
go build ./...— zero errors - GATE 2:
go vet ./...— zero warnings - GATE 3:
go test -race ./...— all tests pass - GATE 4:
go test -cover ./...— >= 80% per package - If any gate fails, fix and re-run until all pass
- GATE 1:
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.
- 1mo ago First seen · 78 lines · 50 tokens per session scan A 2e635851a4ef
code-review-pi is a skill published in the GitHub repository dimetron/pi-go (212 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 895 once invoked, about $0.0002 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
bmad-checkpoint-preview
LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".
ci-orchestrator
Run a CI-like pipeline locally (format, lint, vet, static-analysis, tests) and summarize per-step results with remediation guidance.
code-review
Run a thorough self-review pass on the most recent change.
test-fix
Diagnose and minimally fix a failing test, then re-run.
explore-dataset
Explore an Axiom dataset to understand its schema, fields, volume, and patterns. Use when discovering a new dataset, investigating data structure, or understanding what data is available.
go-conventions
Go code conventions covering Effective Go, error wrapping, golangci-lint, govulncheck, table-driven tests, interfaces, context usage, modules, and concurrency. Load when writing or reviewing Go code.