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 sky-valley/pi --skill pi-go-reviewgit clone --depth 1 https://github.com/sky-valley/piWrote 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/sky-valley/pi/pi-go-review)<a href="https://agentmods.dev/skills/sky-valley/pi/pi-go-review"><img src="https://agentmods.dev/badge/skills/sky-valley/pi/pi-go-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/sky-valley/pi/pi-go-review"><img src="https://agentmods.dev/badge/skills/sky-valley/pi/pi-go-review.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 | $0.00045 | $0.00809 |
| Opus 5 | $0.00023 | $0.00404 |
| Sonnet 5 | $0.00009 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
pi-go-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 12d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-go-review — is the port real Go?
Input: a diff (commit range, or "the uncommitted changes"). Review ONLY the changed code, in context. You are independent of whoever wrote it; do not trust its comments or its tests' assertions.
Charter
The port's promise is "faithful, idiomatic Go that leans into Go's strengths". Faithfulness is the other reviewer's job (pi-parity-review); yours is the Go. A finding must cite file:line and say what idiomatic form replaces it.
Hunt for
- TS transliteration smells:
map[string]anywhere a struct fits;anyplumbing; closures captured where a method belongs; promise-style callback shapes where a channel/context fits; manual index loops over runes/UTF-16 where the stdlib has it (careful: UTF-16 code-unit math is often DELIBERATE parity — check the comment before flagging). - Error discipline: errors returned not panicked (panic only for the
loop's emitPanic protocol);
%wwrapping where callers may unwrap; no swallowed errors (_ =needs a justifying comment). - Concurrency: every goroutine has an exit path; locks released on all
paths (defer or tight func scope); no shared-map mutation without the
documented serialization discipline (see agent/loop.go serialMu pattern);
anything new must pass
-race. - API shape: zero-values useful; options structs over long params;
pointers only for optional/ownership (
*int= "absent" is a deliberate pi-nullish pattern — keep); exported things documented; no stutter (coding.CodingTool). - Resource hygiene: Close/cleanup on error paths, contexts respected, bounded buffers for unbounded input (see the OutputAccumulator port).
- Tests: table-driven where repetitive;
t.TempDir/t.Context; no sleeps-as-sync; race-clean.
Regenerated embedded artifacts (e.g. ai/models_catalog.json)
The unit of review is the STRUCTURAL diff vs the previous embed, not the textual diff (these files are minified single lines). Reading the consuming Go code (e.g. ai/catalog.go, ai/types.go) is required, not out of scope. Validate the artifact against its consuming types: field/enum unions, duplicate JSON keys (encoding/json silently last-wins), null-vs-absent semantics; grep the repo for IDs the regen removed (orphaned defaults/tests); run the consuming package's tests under -race; confirm which upstream version generated it. Cite findings by JSON path, not file:line.
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.
- 12d ago First seen · 62 lines · 45 tokens per session scan A 49b557484dea
pi-go-review is a skill published in the GitHub repository sky-valley/pi (49 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 809 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
code-review
Run a thorough self-review pass on the most recent change.
design-review
Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension and provides actionable fixes.
agents-md
Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects. Use this skill whenever the user asks to create, scaffold, bootstrap, update, or review an AGENTS.md (or agent-instructions, CLAUDE.md, repo guide for agents) file in a codebase. Also trigger when the user says "add AGENTS.md", "make this repo…
go-code-reviewer
Review Go code with a defect-first approach using repository policy (constitution.md first, then AGENTS.md fallback). Use for code review, PR review, quality checks, risk analysis, and regression detection.
go-review-lead
Orchestrate a comprehensive Go code review by triaging code changes, dispatching vertical review skills (security, concurrency, error, logic, performance, quality, test, observability) as parallel agents, then consolidating results into a unified report. Use for full Go PR review or comprehensive code review. Replaces…
go-concurrency-review
Review Go code for concurrency safety and goroutine lifecycle issues including race conditions, deadlocks, goroutine leaks, mutex misuse, and context propagation. Trigger when code contains go func, channels, sync primitives, WaitGroup, errgroup, or goroutine lifecycle management. Use for concurrency-focused review of…