Borrowing it
Nothing to install: this file belongs to gviiisen/repo-context-ledger. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gviiisen/repo-context-ledger/main/AGENTS.mdgit clone --depth 1 https://github.com/gviiisen/repo-context-ledgerWrote 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/instructions/gviiisen/repo-context-ledger/agents-md)<a href="https://agentmods.dev/instructions/gviiisen/repo-context-ledger/agents-md"><img src="https://agentmods.dev/badge/instructions/gviiisen/repo-context-ledger/agents-md/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/instructions/gviiisen/repo-context-ledger/agents-md"><img src="https://agentmods.dev/badge/instructions/gviiisen/repo-context-ledger/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01686 | $0.01686 |
| Opus 5 | $0.00843 | $0.00843 |
| Sonnet 5 | $0.00337 | $0.00337 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
repo-context-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 3d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
Repository context ledger
Before any Ledger call, use current conversation and inspected facts to judge the new delta, not whether task wording looks similar. With sufficient context, routine questions/rechecks/operations use ordinary tools and no new Ledger lifecycle. In a known unfinished task, keep its session/epoch and update only new changes, findings, and results; do not rewrite unchanged background. Similar work on different behavior or inputs still needs its real delta recorded. After a record is completed, new changes require a new record, not reopening history. Query only missing identity/context, without a new classification command, document, or automatic rescan. Reuse execution methods, not stale verification or authorization; necessary fresh checks and relevant code reading remain mandatory.
Resolve an unidentified new request or fresh window with plan --query "<user request>" --tool <agent>. Follow its mode and next_action; clarify when requires_confirmation is true. Inside a known task, retain its session and epoch without repeating plan/status/context/focus unless identity, scope, repository, or an unresolved question changes. Read-only work never starts a session. A bounded configuration change uses start --kind local-config --workflow small-fix → verify --sensitive -- <direct executable and arguments> → finish --path <changed-config>. A known small fix uses start --workflow small-fix → implement → acceptance verify → finish. Use status only to resolve uncertain task state. Prefer an exact reviewed preset; preserve preset trust and ordinary behavior gates.
Runtime mode: bundled. Use the repository .context-ledger/ledger.py entry. In global mode it forwards to the installed Codex Skill under CODEX_HOME (or the user's .codex); keep all configuration and history in this repository, and do not overwrite the forwarder with an old runtime.
For a known scoped small fix, skip context/focus and a separate evidence command; broad dirty work or parallel sessions still requires explicit task-scoped evidence.
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.
- 3d ago Changed · +6 lines · +416 tokens per session fce517bc460f
- 12d ago First seen · 27 lines · 1,270 tokens per session scan A 5e617326cf9a
repo-context-ledger AGENTS.md is an instructions file published in the GitHub repository gviiisen/repo-context-ledger (105 stars, last pushed 4d ago), licensed MIT. It adds 1,686 tokens to every session, about $0.0084 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 instructions, from other repositories
spec-kit AGENTS.md
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
vscode buildNext.instructions.md
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).
langchain AGENTS.md
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.
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).