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/mikuare/code-ledger/agents-mdgit clone --depth 1 https://github.com/mikuare/Code-LedgerWhat 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 | $0.02787 | $0.02787 |
| Opus 5 | $0.01393 | $0.01393 |
| Sonnet 5 | $0.00557 | $0.00557 |
| Haiku 4.5 | $0.00279 | $0.00279 |
Grade A, and why
Code-Ledger 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- Code-Ledger CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeLedger Protocol
One call before you start
Make one call before reading source files or editing anything (CLI: codeledger brief "<the user's request>"; MCP: codeledger_start_task). Pass the user's request in their own words — do not rewrite it, and do not summarise it first.
It answers do_next and gives you the exact next command:
ASK_USER— the repository cannot settle something the request leaves open: which area is meant, or how widely a shared change applies. The questions come with options drawn from the index. Ask the user. Do not choose one silently — picking an interpretation and working on it is the most expensive mistake available here, and it is invisible until the work is finished. When they answer, call again with their answer as--understanding/understanding, in your own words.CONFIRM— the target is settled and there is something worth agreeing on first. State what you understand the task to be — what will change, what will not, how it will be verified — and call again with it asunderstanding.CONFIRMEDmeans your restatement is consistent with the request and names only code this project has. It does not mean the reading is right; only the user can say that.RESUME— this task has been worked on before. Readnext_actionandfailed_attemptsbefore anything else. Those are approaches already known not to work.RECONSIDER— previous attempts changed no symbol, or changed the same symbols repeatedly while verification still failed. Editing again is unlikely to help.PROCEED_WITH_CARE/PROCEED— the target is settled and its footprint is measured. Read what is in scope, then submit your plan tocodeledger handshake.
brief composes resume, clarify, check and progress. Each is still available on its own; the composition exists so the pre-change reading is one call rather than four, because the step that is four calls deep is the step that does not happen.
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.
- yesterday First seen · 83 lines · 2,787 tokens per session scan A b7db9fa743d3
Code-Ledger AGENTS.md is an instructions file published in the GitHub repository mikuare/Code-Ledger (0 stars, last pushed 6d ago), licensed MIT. It adds 2,787 tokens to every session, about $0.0139 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.