Borrowing it
Nothing to install: this file belongs to lbk-open/super-spec. 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/lbk-open/super-spec/main/AGENTS.mdgit clone --depth 1 https://github.com/lbk-open/super-specWrote 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/lbk-open/super-spec/agents-md)<a href="https://agentmods.dev/instructions/lbk-open/super-spec/agents-md"><img src="https://agentmods.dev/badge/instructions/lbk-open/super-spec/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/lbk-open/super-spec/agents-md"><img src="https://agentmods.dev/badge/instructions/lbk-open/super-spec/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 | $0.00808 | $0.00808 |
| Opus 5.5 | $0.00323 | $0.00323 |
| Sonnet 5.5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
super-spec 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 12d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SuperSpec Repository Guide
SuperSpec delivers portable Agent Skills (SKILL.md) from one source for Claude Code, Codex, Pi and OpenCode. This is a prompt-first toolkit, not an application server or runtime workflow engine. Correctness includes valid manifests, complete links, coherent prompt contracts and honest evidence, not live agent behavior proof.
Validation
./scripts/validate.sh
node --test --test-name-pattern='^contract:flags:' scripts/tests/workflow-contracts.test.mjs
claude plugin validate .
ls skills | grep -c '^ss-'
The validator runs all repository static prompt tests. In a delivery workflow, the owner runs selected tests only and the retained verifier owns full validation AFTER independent review. Node is required for repository tests, not prompt execution. Optional native plugin validation is explicitly disclosed when unavailable. Installation/discovery tests alter local agent configuration; run only with consent.
Source and manifests
One skill = one ss-* directory = one SKILL.md, with exactly name and description frontmatter. Keep portable descriptions (at most 1024 characters), no host-specific fields/model overrides. Shared references live in ss-references; guardrails in ss-guardrails. Install all 20 skills side by side: sibling links must survive copying.
Keep the five JSON manifests valid: package.json, .claude-plugin/plugin.json, .claude-plugin/marketplace.json, .codex-plugin/plugin.json, and .agents/plugins/marketplace.json. The package and both plugin versions stay aligned; Pi's ./skills declaration and local marketplace paths remain intact. The local package name is super-spec; do not claim registry/public availability from metadata. Installation uses this checkout, not an assumed published destination.
Coupled interfaces
- Repositories Involved: in proposals and routing.
- Repositories Requiring Fix: / Affected Paths: / Problem ID: in RCA.
- Violated Invariant: / Owning Boundary: / Patch-Style Alternative Rejected:.
- Repo: / Repos: / BASE_SHA: in plans.
- Paired ---SS-RESULT--- with strict taskId/repoId/status/checkpoint/currentFingerprint, reviewEvidence/fullEvidence/delivery/blockers producer and consumer.
- INCOMPLETE_REVIEW fails closed; SUCCESS requires identical current 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.
- 12d ago Changed · -48 lines · -715 tokens per session de39c2197d9d
- 1mo ago First seen · 119 lines · 1,523 tokens per session scan A 39e6770ac416
super-spec AGENTS.md is an instructions file published in the GitHub repository lbk-open/super-spec (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 808 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 2026-08-31.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).