Borrowing it
Nothing to install: this file belongs to aquivalabs/speccy. 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/aquivalabs/speccy/main/AGENTS.mdgit clone --depth 1 https://github.com/aquivalabs/speccyWrote 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/aquivalabs/speccy/agents-md)<a href="https://agentmods.dev/instructions/aquivalabs/speccy/agents-md"><img src="https://agentmods.dev/badge/instructions/aquivalabs/speccy/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/aquivalabs/speccy/agents-md"><img src="https://agentmods.dev/badge/instructions/aquivalabs/speccy/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 | $0.00811 | $0.00811 |
| Opus 5.5 | $0.00324 | $0.00324 |
| Sonnet 5.5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
speccy 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 4d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
speccy is a guided spec-to-implementation pipeline, shipped as a skill: spec → critique → plan → build → review. It runs an adversarial loop over each artifact and delegates heavy work to subagents. This file holds the conventions for anyone, human or agent, changing this repo.
This is a public repo
Nothing here may reference a client, an employer, or another project: no names, no domains, no private details, in any file, commit message, or run artifact. When an example needs a real run, describe it by shape (a spec, a critique round), never by its repo, branch, or feature name.
Conventions live in this file, not in an assistant's memory
A durable project convention belongs here, where every contributor and every agent reads it. Do not stash it in a per-assistant private memory: that hides it from everyone else and from the next tool. When you learn something the whole team should follow, suggest adding it to this file.
Branches and pull requests
main is protected. Branch for your work and open a pull request; do not commit to main directly. The CI job is named status-check, and branch protection requires that exact name, so do not rename it.
Versioning
The plugin version is pre-1.0, so a "minor" release bumps the third digit (0.10.3 → 0.10.4), not the second. CI requires a plugin version bump whenever the skills change, so bump .claude-plugin/plugin.json in the same pull request.
Tests
Run node --test "skills/speccy/test/*.test.mjs" "adapters/codex/test/*.test.mjs" and node test/smoke.mjs --harness claude, and keep them green; the status-check job runs both.
The workflow scripts don't parse standalone
skills/plan-execution/workflow.js and workflow-simple.js combine export const meta (module-level) with a top-level return (function-body-only), so no JS mode parses them and node --check always fails, on main too. They run only through the loader transform; the real syntax gate is loadWorkflow() in adapters/codex/loader.mjs. Don't add a node --check step for them.
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.
- 4d ago First seen · 48 lines · 811 tokens per session scan A 2cf012714aad
speccy AGENTS.md is an instructions file published in the GitHub repository aquivalabs/speccy (14 stars, last pushed 2d ago), licensed MIT. It adds 811 tokens to every session, about $0.0032 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 2026-11-03.
speccy AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| speccy AGENTS.mdaquivalabs/speccy | Instructions file | 14 | 2d ago | MIT | A | 811 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |