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 jeremylongworth-source/AgentSkills --skill write-specgit clone --depth 1 https://github.com/jeremylongworth-source/AgentSkillsWrote 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/jeremylongworth-source/agentskills/write-spec)<a href="https://agentmods.dev/skills/jeremylongworth-source/agentskills/write-spec"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/write-spec/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/jeremylongworth-source/agentskills/write-spec"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/write-spec.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.00351 |
| Opus 5.5 | $0.00023 | $0.00140 |
| Sonnet 5.5 | $0.00012 | $0.00070 |
| Haiku 4.5 | $0.00006 | $0.00035 |
Grade A, and why
write-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 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.
What it actually says
Write Spec
Core Workflow
- Identify the decision, user problem, target segment, product surface, and expected outcome.
- Summarize evidence separately from assumptions and open questions.
- Define goals, non-goals, requirements, user flows, edge cases, dependencies, constraints, and launch considerations.
- Write acceptance criteria that are observable and testable.
- Include analytics, experiment, support, accessibility, QA, and release needs when they affect product success.
- Flag unresolved decisions and owner approvals before implementation starts.
Safety Rules
- Do not present assumptions as customer evidence.
- Do not create roadmap, pricing, legal, support, or launch commitments without approval.
- Do not over-specify implementation details when the engineering approach is intentionally open.
- Escalate when requirements conflict with policy, accessibility, privacy, security, billing, or contractual commitments.
Deliverable Shape
For product specs, provide:
- Problem and audience
- Evidence and assumptions
- Goals and non-goals
- Requirements
- User flow or workflow
- Edge cases and constraints
- Acceptance criteria
- Analytics or validation plan
- Risks, dependencies, and open questions
References
- Read
references/write-spec-checklist.mdwhen writing or reviewing PRDs, feature specs, requirements docs, or implementation briefs.
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.
- 1mo ago First seen · 49 lines · 58 tokens per session scan A 4ac5312c99a6
write-spec is a skill published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 17d ago), licensed MIT. It adds 58 tokens to every session and 351 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 2026-09-03.
Other skills, from other repositories
issue-authoring
Draft or refine IDD-ready GitHub issues, roadmap issues, and sub-issues before the normal IDD execution loop begins. Use when a request is too large or ambiguous for one reviewable change, when work needs decomposition or dependency encoding, or when the user asks for issue drafting, roadmap planning, or…
analiz-task-spec
Use when opening an analiz task for the system-architect - the required fields, what the criteria may say, and what the description must hand over.
answer-workspace-questions
Use when the stakeholder asks a factual or status question about the workspace - call the matching read tool and answer conversationally, without creating tasks or asking for approval.
call-prep
Create or review call prep deliverables with traceable assumptions, decision criteria, ownership, and risk controls. Use when the user asks for call prep planning or analysis.
wicked-garden-product
Product domain skill: 13 user-invokable actions — a11y | acceptance | align | analyze | elicit | listen | mockup | screenshot | strategy | synthesize | ux | ux-review | visual-direction — backed by the rubrics in refs/ and this domain's knowledge-module sub-skills. Use when: "accessibility audit", "WCAG compliance"…
wicked-garden-swarm
Parallel verification-swarm orchestration playbook: fan out N scoped subagents over N units of work (repos / modules / files), then run a SEPARATE verifier wave that re-derives each result from a clean state — self-graded "done" is rejected. Composes the crew agents, the qe semantic-reviewer, /wicked-garden:prove…