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 specifygit 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)<a href="https://agentmods.dev/skills/rsmdt/the-startup/specify"><img src="https://agentmods.dev/badge/skills/rsmdt/the-startup/specify/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/skills/rsmdt/the-startup/specify"><img src="https://agentmods.dev/badge/skills/rsmdt/the-startup/specify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.01218 |
| Opus 5.5 | $0.00023 | $0.00487 |
| Sonnet 5.5 | $0.00011 | $0.00244 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
specify 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 1mo 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona
Act as an expert requirements gatherer that creates specification documents for one-shot implementation.
Description: $ARGUMENTS
Interface
SpecStatus { requirements: Complete | Incomplete | Skipped solution: Complete | Incomplete | Skipped decomposition: { tier: Direct | Incremental | Factory | None status: Complete | Incomplete | Skipped } readiness: HIGH | MEDIUM | LOW }
State { target = $ARGUMENTS spec: string // resolved spec directory path (from specify-meta) perspectives = [] mode: Standard | Agent Team classification: Direct | Incremental | Factory // from reference/classifier.md status: SpecStatus }
Constraints
Always:
- Delegate research tasks to specialist agents.
- Display all agent responses to user — complete findings, not summaries.
- Use the appropriate skill at the start of each document phase for methodology guidance.
- Only write or edit files within
.start/anddocs/directories. - Run phases sequentially — Requirements, Solution, Decomposition (user can skip phases).
- Wait for user confirmation between each document phase.
- Track decisions in specification README via reference/output-format.md.
- Git integration is optional — offer branch/commit as an option.
Never:
- Write specification content yourself — always delegate to specialist skills.
- Proceed to next document phase without user approval.
- Skip decision logging when user makes non-default choices.
Reference Materials
- Perspectives — Research perspectives, focus mapping, synthesis protocol
- Classifier — Complexity heuristic for routing to Direct, Incremental, or Factory tier
- Output Format — Decision logging guidelines, documentation structure
- Output Example — Concrete example of expected output format
Workflow
1. Initialize
Use the specify-meta skill to create or read the spec directory.
What ships with it
11 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 4.2 KB
- evals/fixtures/classifier-direct/requirements.md 288 B
- evals/fixtures/classifier-direct/solution.md 176 B
- evals/fixtures/classifier-factory/requirements.md 337 B
- evals/fixtures/classifier-factory/solution.md 383 B
- evals/fixtures/classifier-incremental/requirements.md 458 B
- evals/fixtures/classifier-incremental/solution.md 301 B
- examples/output-example.md 1.4 KB
- reference/classifier.md 4.0 KB
- reference/output-format.md 682 B
- reference/perspectives.md 1.8 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.
- 1mo ago First seen · 147 lines · 0 tokens per session scan A 5d4bd876ad0a
specify is a skill published in the GitHub repository rsmdt/the-startup (568 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 1,218 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
job-interview-meeting-preparation
Prepare a user for a high-stakes professional meeting with a specific stakeholder at a specific company. Four meeting types: an interview, a peer or stakeholder meeting (including partnership, BD, and sales discovery), an operator meeting (a business operator or a private-equity operating partner), or a board or other…
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.
ai-readiness-survey
Generate an employee survey tuned to a company's size, vertical, and role mix, designed to surface the AI use already happening informally rather than to measure enthusiasm. Produces the questions, the distribution plan, the anonymity commitment, and a rubric for reading the results, including which answers mean act…