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/shin4141/agents-md-compactor/agents-mdgit clone --depth 1 https://github.com/shin4141/agents-md-compactorWrote 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/shin4141/agents-md-compactor/agents-md)<a href="https://agentmods.dev/instructions/shin4141/agents-md-compactor/agents-md"><img src="https://agentmods.dev/badge/instructions/shin4141/agents-md-compactor/agents-md.svg" alt="Measured on agentmods" 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 | $0.01567 | $0.01567 |
| Opus 5 | $0.00783 | $0.00783 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
agents-md-compactor 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Receiver Operating Capsule
This repository is the standalone shin4141/agents-md-compactor product. It is
not a V13-series repository and must not import V13 production code. V11
Reconnectable Forgetting is the primary product concept; V13 supplies only the
operating discipline below.
1. Ownership and Authority
- Shin is the final Decision Owner.
- This execution thread is the sole implementation owner. Do not create a competing implementation thread or ask Shin to shuttle routine prompts.
- The implementation owner may choose ordinary implementation details within the frozen v0.1 boundary.
- Product direction, public claims, pricing, release, externalization, branding, and risk-tolerance changes require Shin's approval.
- Prior work, an artifact, or a passing test does not create new authority.
2. Current Gate and Completion
Current Gate:
The reviewed Fictional Sample 001 ancestry marker is
bc5e513e4891bd912a8515c9ea98abb8cd27d755.
Before selecting the Gate, refresh canonical origin/main and check whether
that marker is its ancestor:
git fetch origin main
git merge-base --is-ancestor bc5e513e4891bd912a8515c9ea98abb8cd27d755 origin/main
- If it is not an ancestor, the Gate is:
HOLD — Fictional Sample 001 review / merge. Missing Closure includes review / merge of Draft PR #5, Fable read-only review, and any separately authorized README/Fable-link or announcement decision. The next authorized action is review and, only with Shin's authorization, merge PR #5. - If it is an ancestor, the Gate is:
HOLD — Fable read-only review separately unauthorized. PR #5 review / merge is no longer Missing Closure. The next stage is Fable read-only review, only with separate Shin authorization.
Do not infer settlement from the feature branch, the PR's existence, or a stale local checkout. While the marker is absent, PR #5 has not reached canonical main and does not authorize Fable.
Do not claim a stage complete from file existence, a running UI, partial generation, or a happy-path test alone. Each stage must record:
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 First seen · 168 lines · 1,567 tokens per session scan A d2005f9f8db1
agents-md-compactor AGENTS.md is an instructions file published in the GitHub repository shin4141/agents-md-compactor (2 stars, last pushed 25d ago), licensed Apache-2.0. It adds 1,567 tokens to every session, about $0.0078 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
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).
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.
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.
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).
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.