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/claude-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 | $0.02196 | $0.02196 |
| Opus 5 | $0.01098 | $0.01098 |
| Sonnet 5 | $0.00439 | $0.00439 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
evolve-loop CLAUDE.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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions (Claude Code)
Read AGENTS.md first — cross-CLI invariants + the 12 Core Agent Rules. This file is the Claude Code overlay (digest). Full runtime detail — env-var table, operator commands, ship classes, publishing pipeline — lives in docs/operations/runtime-reference.md. Read it before touching loop behavior, flags, gates, or releases. Release notes: CHANGELOG.md. Operating policy (canonical, environment-independent): docs/operations/operating-policy.md — pipeline issues are fixed console-first at maximum reasoning; routing is typed plumbing; salvage before requeue; wiring proofs mandatory. The repo, not session memory, is the source of truth for these rules.
Automation Loop Guardrails
- When running the evolve loop or any batch/merge-train automation, evaluate output after EVERY cycle. If 2 consecutive cycles produce zero ships (0 merged PRs), STOP the loop immediately and root-cause the pipeline before running another wave.
- Never let a batch run more than 2 unproductive waves "to see if it self-corrects".
- ADR-0072 reconciliation: a zero-ship streak is SYSTEM-fail evidence — HALT + P0 applies. This does not conflict with "never stop the queue", which governs task-level failures.
Status Reporting
When reporting on a batch or pipeline run, always include: cycles run, ships/lanes completed (e.g. 2/2), open PR numbers, failing CI job names with failure class, and the specific next action. Do not report "running" or "in progress" as a status without these numbers.
Session conventions
- Confirm direction first: multi-step/multi-cycle work needs a 3-bullet plan + approval. Single-cycle bug fixes, file-path-specified tasks, and approved-plan tasks are exempt.
- Output discipline: summaries with
file:linerefs; >300-line findings go to a markdown file, not chat. - Long-running jobs: verify health after launch (exit codes, log tail); checkpoint every cycle so
--resumeworks; surface failures immediately.
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 · 79 lines · 2,196 tokens per session scan A 756a9964d9c1
evolve-loop CLAUDE.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 2,196 tokens to every session, about $0.0110 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
ForgeDock AGENTS.md
AGENTS.md instructions for RapierCraftStudios/ForgeDock, covering forgedock for codex, codex entry model, runtime rules, scope boundaries and first references.
agent-skills AGENTS.md
Instructions for AsyrafHussin/agent-skills, covering agent skills repository, skills overview, usage and contributing.
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.
falsegreen-skill CLAUDE.md
Instructions for vinicq/falsegreen-skill, covering claude.md - falsegreen-skill, what this project is, public repo boundary, maintenance rules and default model guidance.
autonomous-dev CLAUDE.md
Claude Code instructions for akaszubski/autonomous-dev, covering autonomous-dev, critical rules, maintainer escape hatches, architecture and code navigation.