benbrownandClaude Fable 5
477c5472dd
The SKILL.md Agent Skills standard (agentskills.io) is now read natively by Codex, Copilot, VS Code, Cursor, Gemini CLI, opencode, Goose, Amp, Zed, Factory, and ZeroClaw — so the portable move is not per-harness adapter files (forked content that drifts) but one canonical skill placed where each harness actually looks. - Spec-compliant frontmatter: license, compatibility (the Linux-only measurement story, stated up front), version/author/tags top-level (ZeroClaw's runtime reads those; the spec ignores unknown fields). reference/ renamed to references/ per the spec's conventional layout. - .agents/skills/peltier/ mirror: the cross-tool convergence path (Codex, Zed, Cursor, Gemini CLI, Copilot, opencode, Goose, Amp). Byte-identical to the .claude canonical, enforced by CI — drift between the two copies is a red build, not a footnote. - AGENTS.md at the repo root for the ~20 harnesses that read it (Claude Code does not; CLAUDE.md remains its file). Deliberately thin: it points at CLAUDE.md and the skill instead of restating rules. - scripts/install-skill.sh: stamps a consumer repo at both discovery paths (--layout claude|agents|both), or emits a script-less --zeroclaw-variant. ZeroClaw's skill security policy blocks script files by default (skills.allow_scripts off) — its audit rejected the full skill and passes the variant, verified against the real zeroclaw binary. The variant loses nothing: preflight.sh still exists exactly once, in the peltier checkout the skill already requires, and SKILL.md now documents running it from there. Re-implementing preflight inline is named as a refusal condition. - CI (skill-preflight): frontmatter upgraded to a full Agent Skills spec conformance check on BOTH copies (name rules, dir match, description and body limits, metadata string-map), plus mirror equality and a functional installer test (both layouts identical to canonical, variant carries no scripts/, nonexistent target refused). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
1.6 KiB
peltier.io — agent entry point
This file exists for AGENTS.md-reading harnesses (Codex, Jules, Cursor, Zed, Amp, Copilot coding agent, Gemini CLI, …). It is deliberately thin: the binding project rules live in one place, not here.
Working on this repo
Read CLAUDE.md first and treat it as binding regardless of which harness you are. It holds the non-negotiables (no unverified performance claims, measure-before-optimizing, hard equivalence gates, the append-only ledger, the trust-layer write boundary) and the honest current state of every subsystem. The engineering spec is SPEC.md. Commands live in the justfile. The pipeline is Linux/POSIX-only at runtime; Windows compiles the workspace but cannot run it.
Two hard rules that bear repeating even in a pointer file:
- Never claim a performance number without its confidence interval and workload. If you did not run the gates, the number does not exist.
- The trust layer (
crates/,config/,corpora/) is read-only to optimization agents. Patches touch only allowlisted paths undertargets/<name>/.
Verifying performance changes (any repo, any harness)
This repo ships its trust layer as an Agent Skill:
.claude/skills/peltier/SKILL.md —
mirrored byte-identically at .agents/skills/peltier/ for harnesses that
discover skills there (CI enforces the mirror). If your harness auto-loads
skills from either path, use it whenever a task involves proving or refuting
a speedup. If not, read that SKILL.md and follow it manually — starting with
scripts/preflight.sh, whose refusal is final.