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/lbk-open/super-spec/agents-mdgit clone --depth 1 https://github.com/lbk-open/super-specWhat 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 | $0.01523 | $0.01523 |
| Opus 5 | $0.00762 | $0.00762 |
| Sonnet 5 | $0.00305 | $0.00305 |
| Haiku 4.5 | $0.00152 | $0.00152 |
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 yesterday.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SuperSpec — Repository Guide
SuperSpec is a spec-driven development toolkit for AI coding agents, shipped as portable Agent Skills (SKILL.md) that work across Claude Code, OpenAI Codex, Pi, and OpenCode from a single source — no per-platform builds.
This is a prompt/documentation repository: there is no application code, build step, or test suite. "Correctness" here means valid manifests, resolvable cross-references, and skills whose instructions match the documented design.
Verification commands
./scripts/validate.sh # the full check suite — run before pushing (CI runs it too)
claude plugin validate . # Claude Code plugin + marketplace manifests
ls skills | grep -c '^ss-' # skill count — INSTALL.md asserts this number
grep -rn 'ss-<old-name>' skills docs *.md # after any rename/delete: zero dangling refs
End-to-end discovery checks (optional, used before releases):
claude plugin marketplace add ./ && claude plugin install super-spec@super-spec
cp -R skills /tmp/x/.agents/skills && cd /tmp/x && opencode debug skill # lists ss-*
Architecture
One source, four runtimes
skills/ss-<name>/SKILL.md is the single source of truth. Each platform consumes it
through its own manifest, all committed at the repo root:
- Claude Code —
.claude-plugin/plugin.json+marketplace.json; the repo root is the plugin, skills auto-discovered. - Codex —
.codex-plugin/plugin.json+.agents/plugins/marketplace.json; the repo doubles as a Codex plugin marketplace. - Pi —
package.json(keywords: ["pi-package"],"pi": {"skills": ["./skills"]}). - OpenCode — no package manager; users install via
npx skillsor copy into a discovery path.
Keep version in sync across all three plugin manifests when releasing — releases
are automated with release-please; see RELEASING.md. INSTALL.md is the
agent-executable install/upgrade/uninstall walkthrough.
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.
- yesterday 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 (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 1,523 tokens to every session, about $0.0076 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
skills CLAUDE.md
Instructions for wondelai/skills, covering claude.md, repository purpose, repository structure, current skills (65) and skill file format.
dev-agent-skills CLAUDE.md
Instructions for fvadicamo/dev-agent-skills, covering claude.md, project overview, architecture, key file: marketplace.json and skill anatomy.
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
qa-orchestra CLAUDE.md
Instructions for Anasss/qa-orchestra, covering qa orchestra — claude code instructions, what this project is, quick start, 1. clone into your workspace and 2. fill in your project context.
autorun CLAUDE.md
Claude Code instructions for ahundt/autorun, a project described as: Claude Code & codex plugin + Gemini cli extension to keep ai running, keep data safe, plan better, and keep running until tasks are done.
chealth CLAUDE.md
Instructions for danielithomas/chealth, covering claude.md, project purpose, language & tooling, build & test and architecture.