Borrowing it
Nothing to install: this file belongs to shin4141/agents-md-compactor. 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/shin4141/agents-md-compactor/main/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/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/shin4141/agents-md-compactor/agents-md"><img src="https://agentmods.dev/badge/instructions/shin4141/agents-md-compactor/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 | $0.01567 | $0.01567 |
| Opus 5.5 | $0.00627 | $0.00627 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 3mo ago), licensed Apache-2.0. It adds 1,567 tokens to every session, about $0.0063 per session on Opus 5.5. 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.
agents-md-compactor AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agents-md-compactor AGENTS.mdshin4141/agents-md-compactor | Instructions file | 2 | 3mo ago | Apache-2.0 | A | 1,567 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |