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 skills/ai-driven-dev/framework/05-specnpx skills add ai-driven-dev/framework --skill 05-specgit clone --depth 1 https://github.com/ai-driven-dev/frameworkWhat 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 | $0.00061 | $0.00859 |
| Opus 5 | $0.00030 | $0.00430 |
| Sonnet 5 | $0.00012 | $0.00172 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
aidd-pm:05:spec 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: spec
Produces a complete spec from a free-form human request. The spec is the contract between human intent and downstream agents (planner, implementer, reviewer). It is immutable once validated.
When to use
- A human types
/spec <request>to draft a spec - The
aidd-dev:00:sdlcorchestrator invokes this skill at Phase 1 of a run - An existing spec failed reviewer validation and needs refinement based on findings
When NOT to use
- A validated spec already exists → use it directly, no need to regenerate
- The user only wants a single requirement clarified → use
aidd-pm:04:clarity - The user wants a full PRD with stakeholders, OKRs, and rollout plan → use
aidd-pm:03:prd(more granular than a spec)
Inputs
At least one of request, prd_path, or existing_spec is required.
request: <free-form human description, optional>
prd_path: <path to an existing PRD file, optional — extracted into a spec>
existing_spec: <optional path — for refinement runs>
findings: <optional — reviewer findings to address>
working_dir: <where the spec.md will be written>
Priority when multiple are provided:
existing_spec + findings→ refinement run (rewrite to address findings)prd_path→ extract scope, target, constraints, non-goals, done-when from the PRD into a normalized specrequest→ generate from scratch using the template
Outputs
spec_path: <path to the generated spec.md>
status: draft | refined
notes: <ambiguities, assumptions made, questions for the human>
Behavior
- Refinement (
existing_spec+findings): load both, address each finding, rewrite the spec. - PRD extraction (
prd_path): parse the PRD, extract target / hard constraints / non-goals / done-when into the normalized spec structure. Fields the PRD doesn't cover are markedTBD: <precise question>. Implementation details from the PRD (libraries, patterns, file layout) are dropped — they belong to the plan. - From scratch (
requestonly): produce a draft spec from the request usingassets/spec-template.mdas the structure. - The spec must contain every required section listed in
assets/spec-validator.yml. When information is missing, mark itTBD: <precise question>rather than guess. The reviewer will flag it and the human can answer in the next iteration. - Write the spec to
working_dir/spec.md. - Return the path and status.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 76 lines · 61 tokens per session scan A 4312ad75dcca
aidd-pm:05:spec is a skill published in the GitHub repository ai-driven-dev/framework (445 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 859 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
smoke-test
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
zeroclaw
Help users operate and interact with their ZeroClaw agent instance — through both the CLI (zeroclaw commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API…
github-issue-triage
Issue triage and lifecycle management agent for ZeroClaw. Use this skill whenever the user wants to: triage open issues, close stale/duplicate/fixed issues, apply labels, run a backlog sweep, enforce the current issue stale policy, or handle a specific issue. Trigger on: 'triage issues', 'issue triage', 'sweep…