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-triagegit 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-triage)<a href="https://agentmods.dev/skills/sky-valley/pi/pi-triage"><img src="https://agentmods.dev/badge/skills/sky-valley/pi/pi-triage/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-triage"><img src="https://agentmods.dev/badge/skills/sky-valley/pi/pi-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Anti-Refusal · line 17 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00057 | $0.05833 |
| Opus 5 | $0.00028 | $0.02916 |
| Sonnet 5 | $0.00011 | $0.01167 |
| Haiku 4.5 | $0.00006 | $0.00583 |
Grade A, and why
pi-triage 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 4d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-triage — port-or-not verdict for upstream changes
Input: one or more upstream main-line shas (or a range A..B). Each unit is a
first-parent change: a merged PR is ONE unit, analyzed via git diff <sha>^1..<sha>.
Setup
- Upstream clone:
$PI_UPSTREAM_DIRif set, else~/.cache/pi-upstream. If missing:git clone https://github.com/earendil-works/pi "$dir". Alwaysgit fetch origin mainfirst, thengit -C "$dir" checkout -B main origin/mainto keep the checkout from drifting (it is a read-only mirror; the harness extracts bygit archive <sha>, so this is safe). - Never judge from the working tree — name a sha.
git show <sha>:<path>,git diff <sha>^1..<sha>,git grep <pattern> <sha> -- <path>. A stale checkout can show the exact opposite of what the pin holds (2026-08-11: the tree was ~2 months behind and read as though a ported change had been reverted), and a fresh one is atorigin/main, which is ahead of the pin. - The authoritative scope boundary is
docs/UPSTREAM.md-> "The scope boundary" — the exclusion tests E1 and E3, rewritten 2026-08-27. Read it before judging anything. It replaced an exclusion path-list; the tests beat every list, including the tables in this file. Also read "Scope queue" (what is IN scope but has no Go base yet) and the "Current pin" table.
Per change, produce:
- WHY — intent, from the commit/PR message (
git log -1 --format=%B) and any linked issue number in it. - WHAT — read the actual diff (
git diff <sha>^1..<sha> --statthen the hunks for non-trivial files). Note behavior, constants, model-visible strings, new/changed tests. - SCOPE — verdict, one of:
-
port— touches behavior we ported.Scope is decided by the EXCLUSION TESTS (E1 and E3) in
docs/UPSTREAM.md-> "The scope boundary" (rewritten 2026-08-27). Read them; they are authoritative over this table. A hunk isn/aiff one fires; otherwise it is IN. The table below is a derived convenience — if it and a test disagree, the test wins, you port accordingly, and you fix the table in the same commit.
-
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.
- 4d ago Changed · +12 lines 35d1c1a24cdf
- 9d ago First seen · 299 lines · 57 tokens per session scan A 53eac6478c66
pi-triage is a skill published in the GitHub repository sky-valley/pi (48 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 5,833 once invoked, about $0.0003 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
write-terva-skill
Author a new terva skill, a reusable SKILL.md instruction set that terva loads on demand. Install it where terva discovers it, in the project .terva/skills/ or the global $TERVAHOME/skills/. Use for create/add/write-a-skill requests, not extensions.
write-terva-locale
Translate the terva interface into another language, complete or fix a locale, or wrap new strings for translation. Use when the user asks to localize terva or to add or finish a language (fi, pt-BR, ...). Also use to edit translated text or to contribute a translation upstream.
write-terva-lore
Author terva lore. Lore is context that a person authors in files. terva injects it only when it is keyword-relevant, or always-on. Use to create/add/write lore, "world info", a lorebook entry, keyed background, or a book of facts for a character.
grilling
Interview the user before you build, so the open decisions are theirs and not yours. Use when the user says to grill them, or asks you to interview them first.
handoff
Compact the current session into a handoff document. A fresh session or another agent can pick it up with no need to re-derive context. Use when asked to hand off, hand over, wrap up for another session or agent, or park work mid-stream.
house-style
Apply before you write or edit prose, such as a README.md, documentation, a comment, or a commit message. It covers release notes and skill or persona bodies too. Also use when the user asks you to clean up prose, or to cut machine tells.