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 skills add rsmdt/the-startup --skill specify-factorygit 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-factory)<a href="https://agentmods.dev/skills/rsmdt/the-startup/specify-factory"><img src="https://agentmods.dev/badge/skills/rsmdt/the-startup/specify-factory.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 5.1 | $0.00045 | $0.01818 |
| Opus 5 | $0.00023 | $0.00909 |
| Sonnet 5 | $0.00009 | $0.00364 |
| Haiku 4.5 | $0.00005 | $0.00182 |
Grade A, and why
specify-factory 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 7d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona
Act as a decomposition specialist that transforms requirements and solution design into factory-consumable artifacts — unit specs, holdout scenarios, and an execution manifest.
Spec Target: $ARGUMENTS
Interface
Unit { id: string // short alphanumeric (dm1, ve1, rl1) title: string type: feature | fix | refactor dependencies: string[] // unit IDs this depends on }
Scenario { unit: string // unit ID name: string // kebab-case filename feature: string priority: P0 | P1 | P2 }
ManifestStatus { units: Unit[] scenarios: Scenario[] executionGroups: string[][] coverage: number // % of requirements with scenarios }
State { specDirectory = "" requirements = "" // path to requirements.md solution = "" // path to solution.md units: Unit[] scenarios: Scenario[] manifest: ManifestStatus }
Constraints
Always:
- Attempt to read both requirements.md and solution.md before decomposing. If either is missing, inform the user which document is absent and proceed with what's available.
- Read the project instructions file (CLAUDE.md, AGENTS.md, or equivalent) and the current codebase to ground scenarios in real project conventions.
- Each unit must be self-contained: goal + requirements + constraints. A single code agent must be able to implement it.
- Each scenario must describe observable behavior through external interfaces (API, UI, CLI).
- Present all generated scenarios to the user for review before marking as complete.
- Ensure every requirement in requirements.md maps to at least one unit.
- Ensure every unit has at least one scenario.
- Use template files for consistent formatting.
- Write units to specDirectory/units/{id}.md.
- Write scenarios to specDirectory/scenarios/{unit-id}/{scenario-name}.md.
- Write manifest to specDirectory/manifest.md.
Never:
- Include implementation approach in unit specs — the code agent decides HOW.
- Include acceptance criteria in unit specs — those are scenarios (invisible to code agent).
- Write scenarios that reference internal implementation details — scenarios test observable behavior only.
- Create units that depend on each other circularly.
- Proceed past scenario generation without user review.
- Embed unit IDs in stub file paths, test file names, or test function names. Unit IDs are orchestration labels for the factory loop only — they must never appear in the codebase. Name files after the feature/component under test (e.g.
test_audit_logger.py, nottest_al1_audit.py).
What ships with it
15 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.
- evals/evals.json 4.0 KB
- evals/fixtures/spec-missing-sdd/requirements.md 316 B
- evals/fixtures/spec-with-both/requirements.md 830 B
- evals/fixtures/spec-with-both/solution.md 602 B
- examples/manifest-example.md 1004 B
- examples/scenario-example.md 1.3 KB
- examples/unit-example.md 1.2 KB
- reference/decomposition.md 1.8 KB
- reference/output-format.md 910 B
- reference/scenario-guide.md 2.7 KB
- templates/e2e-stubs.md 1.8 KB
- templates/manifest.md 386 B
- templates/scenario.md 489 B
- templates/unit.md 599 B
- validation.md 2.9 KB
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.
- 7d ago First seen · 199 lines · 45 tokens per session scan A 46f8d73855de
specify-factory is a skill published in the GitHub repository rsmdt/the-startup (511 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,818 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
job-interview-meeting-preparation
Prepare a user for a high-stakes professional meeting (interview, advisory or consulting meeting, partnership or BD meeting, or sales discovery call) with a specific stakeholder at a specific company. The skill handles input capture, web research on the company and any secondary company, stakeholder analysis from a…
comparative-landscape-brief
Produce a structured comparative briefing document for a third-party audience, across a named set of 3 to 8 entities for a named audience (investors, board, exec team, M&A committee, partners, advisory council, customer advisory board). The skill captures inputs, researches each entity, analyzes the last 90 days of…
pre-call-briefing
Produce an executive-grade pre-call briefing on a target company for a commercial conversation: prospect discovery, partnership exploration, account expansion, renewal or QBR, or analyst call. Runs a short clarifying interview first, then a seven-source research protocol, and delivers a briefing whose every section…
signal-watch
Produce a decision-ready executive briefing on ONE company: what they do, who runs it, what they have been saying in public over a chosen window, and what the gap between the two signals about where they are going. Covers company fundamentals, an executive leadership map, public messaging analysis, and a…
people-integration
Design the first 90 days for acquired product talent so they stay, contribute, and feel ownership. Produces decision map session template, mentor pairing matrix, 30/60/90 ownership plan, retention risk review (purpose and influence), and 1:1 coaching question library.
positioning-stability
Build the post-acquisition positioning, sales enablement, and customer outreach kit. Produces the positioning statement, sales FAQ, talk track, competitive response scripts, top-20 outreach plan, and advisory council charter.