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/rsmdt/the-startup/specify-metanpx skills add rsmdt/the-startup --skill specify-metagit clone --depth 1 https://github.com/rsmdt/the-startupWrote 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/skills/rsmdt/the-startup/specify-meta)<a href="https://agentmods.dev/skills/rsmdt/the-startup/specify-meta"><img src="https://agentmods.dev/badge/skills/rsmdt/the-startup/specify-meta.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00803 |
| Opus 5 | $0.00021 | $0.00402 |
| Sonnet 5 | $0.00008 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
specify-meta 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona
Act as a specification workflow orchestrator that manages specification directories and tracks user decisions throughout the Requirements → Solution → Decomposition workflow. The Decomposition phase produces one of three artifact families based on the tier chosen by the specify classifier: Direct (no artifacts), Incremental (plan/ directory), or Factory (manifest.md + units/ + scenarios/).
Interface
SpecStatus { id: string // 3-digit zero-padded (001, 002, ...) name: string directory: string // .start/specs/[NNN]-[name]/ (legacy: docs/specs/) phase: Initialization | Requirements | Solution | Decomposition | Ready decomposition_tier: Direct | Incremental | Factory | None documents: { name: string status: pending | in_progress | completed | skipped notes?: string }[] }
State { specId = "" currentPhase: Initialization | Requirements | Solution | Decomposition | Ready decompositionTier: Direct | Incremental | Factory | None documents: [] }
Constraints
Always:
- Use spec.py (co-located with this SKILL.md) for all directory operations.
- Create README.md from template.md when scaffolding new specs.
- Log all significant decisions with date, decision, and rationale.
- Confirm next steps with user before phase transitions.
Never:
- Create spec directories manually — always use spec.py.
- Transition phases without updating README.md.
- Skip decision logging when user makes workflow choices.
Reference Materials
- Spec Management — Spec ID format, directory structure, script commands, phase workflow, decision logging, legacy fallback
- README Template — Template for spec README.md files
Workflow
1. Scaffold
Create a new spec with an auto-incrementing ID.
- Run
Bash("spec.py \"$featureName\""). - Create README.md from template.md.
- Report the created spec status.
2. Read Status
Read existing spec metadata.
- Run
Bash("spec.py \"$specId\" --read"). - Parse TOML output into SpecStatus.
- Suggest the next continuation point:
What ships with it
3 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.
- 4d ago First seen · 105 lines · 42 tokens per session scan A 7cf79a1fd2a6
specify-meta is a skill published in the GitHub repository rsmdt/the-startup (511 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 803 once invoked, about $0.0002 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
atomic-issues-prs
Publish a change-set as atomic GitHub issues or PRs. Use when the user says "atomic PRs" or wants one issue/PR per logical change.
user-story-generator
Transforms requirements into user stories with Given/When/Then acceptance criteria ready for sprint planning and Jira. Use when user needs to write user stories, create Jira tickets, define acceptance criteria, or says "user stories", "acceptance criteria", "sprint backlog", "Jira tickets", "as a user I want"…
ambiguity-resolver
Structures a brief HANDED DOWN by a stakeholder (boss, exec, another team) into a one-page problem statement with scope boundaries and a named decision owner. Use when the PM says "мне спустили задачу", "I've been asked to look into Y", "руководство хочет X", "CEO попросил разобраться" — a request the PM didn't…
setup-initiative
Guides the PM through an initiative alignment checklist — metric, baseline, target, stakeholders, success/kill criteria. Use before a gate, when the PM says "setup initiative", "set the target", "define success criteria", "align on goals", or when the coverage map shows Frame incomplete. NOT a prerequisite for…
go
Execute the next undone task(s) from a sprint's TASKS.md by dispatching the magi-developer subagent (Sonnet by default). Updates WORKS.md as a development log. Pauses for user confirmation before any commit. Default behavior auto-parallelizes tasks with disjoint file scopes; --parallel forces parallel, --sequential…
status
Terse "where am I, what's next" printer for magi-workflow projects. Outputs only the current project state, sprint dir (if any), suggested next command, and any active warnings — typically 3–6 lines. Use this when you're mid-flow and just need a quick orientation; reach for /magi:help when you want the full command…