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 agentmods add instructions/mickeyyaya/evolve-loop/agents-mdgit clone --depth 1 https://github.com/mickeyyaya/evolve-loopWhat 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 | $0.04503 | $0.04503 |
| Opus 5 | $0.02252 | $0.02252 |
| Sonnet 5 | $0.00901 | $0.00901 |
| Haiku 4.5 | $0.00450 | $0.00450 |
Grade A, and why
evolve-loop AGENTS.md 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 2d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Cross-CLI Canonical Instructions
Read this file first if you are an AI agent (Claude Code, Codex CLI, Antigravity/agy, Ollama, Gemini CLI, or generic) working in this repository. It is the source-of-truth for cross-CLI invariants. CLI-specific runtime details live in companion files: CLAUDE.md, GEMINI.md. All three reference back to this document.
Operating policy (canonical): docs/operations/operating-policy.md carries the environment-independent process rules — pipeline-integrity handling (console-first, maximum reasoning), queue/routing authority, engineering standards, failure-handling contract, release policy — each with the incident evidence behind it. A clean environment inherits the full policy from the repo alone; session memory is only an advisory mirror.
What evolve-loop is
A self-evolving development pipeline that orchestrates specialized phase agents (Intent, Scout, Triage, TDD, Builder, Auditor, plus retro/memo) through a fixed spine per cycle (Intent → Scout → Triage → [TDD] → Build → Audit → Ship → Learn). Tier-1 kernel hooks enforce phase ordering, role-scoped write paths, atomic ship semantics, ledger SHA verification, and v8.37+ tamper-evident hash-chained recording.
Runtime note (Go-only): The Go binary (
go/bin/evolve) is the sole runtime entrypoint. The bashlegacy/scripts/tree were removed in the Go-only consolidation — there is no bash fallback. Every operation below is a nativeevolve <subcommand>or a function ingo/internal/.... For the history of the bash→Go port, see docs/migration-from-bash.md.
Cross-CLI invariants (the universal rules)
These rules apply regardless of which CLI you are running under. They are STRUCTURAL — enforced by kernel hooks, not by prompt instructions.
1. Pipeline ordering is non-negotiable
Phases run Scout → Builder → Auditor → Ship/Record in that exact order. Phase ORDER is enforced by the Go orchestrator state machine (go/internal/core); the phase-gate kernel hook (evolve guard phase, rewired per ADR-0075 onto the Agent|Task matcher) denies in-process subagent dispatch while a cycle is active. The emergency operator override is the explicit evolve guard phase --bypass CLI flag; use is logged loudly and considered a CRITICAL violation.
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.
- 2d ago First seen · 141 lines · 4,503 tokens per session scan A 7e080617b851
evolve-loop AGENTS.md is an instructions file published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,503 tokens to every session, about $0.0225 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 2026-08-31.
Other instructions, from other repositories
tdd-guard CLAUDE.md
Instructions for nizos/tdd-guard, covering tdd guard, project goal, development workflow, commit guidelines and project structure.
procoder tests.instructions.md
Instructions for azrtydxb/procoder, covering tests in procoder, every test carries its mutation, assertions, portability and fixtures.
ForgeDock AGENTS.md
AGENTS.md instructions for RapierCraftStudios/ForgeDock, covering forgedock for codex, codex entry model, runtime rules, scope boundaries and first references.
vscode_abap_remote_fs CLAUDE.md
Instructions for marcellourbani/vscode_abap_remote_fs, covering abap fs development guidelines, workflow and constraints.
dxkit CLAUDE.md
Instructions for vyuh-labs/dxkit, covering claude.md — dxkit development rules, architecture rules, 1. tool invocation goes through the registry, 2. never duplicate tool invocation logic and 3. language facts come from detect.ts.
devkit CLAUDE.md
Instructions for 5uck1ess/devkit, covering claude.md, layout, architectural invariants, conventions and fixing this file.