Knowledge Work Plugins is an open-source collection of Claude extensions organized around roles such as productivity, sales, and customer support. Each plugin combines role-specific guidance, connectors, commands, and sub-agents so knowledge workers can use Claude with their team’s tools and processes. The catalogue entries are examples of, or workflows from, this plugin collection.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsnpx agentmods add skills/anthropics/knowledge-work-plugins/write-specWrote 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/anthropics/knowledge-work-plugins/write-spec)<a href="https://agentmods.dev/skills/anthropics/knowledge-work-plugins/write-spec"><img src="https://agentmods.dev/badge/skills/anthropics/knowledge-work-plugins/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/anthropics/knowledge-work-plugins/write-spec"><img src="https://agentmods.dev/badge/skills/anthropics/knowledge-work-plugins/write-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 55 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00060 | $0.02732 |
| Opus 5.5 | $0.00024 | $0.01093 |
| Sonnet 5.5 | $0.00012 | $0.00546 |
| Haiku 4.5 | $0.00006 | $0.00273 |
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.
Copies of this mod
7 near-identical copies found in the catalogue:
- write-spec — 100% identical, 0 lines differ
- write-spec — 100% identical, 0 lines differ
- write-spec — 98% identical, 9 lines differ
- write-spec — 95% identical, 24 lines differ
- write-spec-th — 91% identical, 8 lines differ
- feature-spec — 89% identical, 106 lines differ
- feature-spec — 89% identical, 106 lines differ
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Spec
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Write a feature specification or product requirements document (PRD).
Usage
/write-spec $ARGUMENTS
Workflow
1. Understand the Feature
Ask the user what they want to spec. Accept any of:
- A feature name ("SSO support")
- A problem statement ("Enterprise customers keep asking for centralized auth")
- A user request ("Users want to export their data as CSV")
- A vague idea ("We should do something about onboarding drop-off")
2. Gather Context
Ask the user for the following. Be conversational — do not dump all questions at once. Ask the most important ones first and fill in gaps as you go:
- User problem: What problem does this solve? Who experiences it?
- Target users: Which user segment(s) does this serve?
- Success metrics: How will we know this worked?
- Constraints: Technical constraints, timeline, regulatory requirements, dependencies
- Prior art: Has this been attempted before? Are there existing solutions?
3. Pull Context from Connected Tools
If ~~project tracker is connected:
- Search for related tickets, epics, or features
- Pull in any existing requirements or acceptance criteria
- Identify dependencies on other work items
If ~~knowledge base is connected:
- Search for related research documents, prior specs, or design docs
- Pull in relevant user research findings
- Find related meeting notes or decision records
If ~~design is connected:
- Pull related mockups, wireframes, or design explorations
- Search for design system components relevant to the feature
If these tools are not connected, work entirely from what the user provides. Do not ask the user to connect tools — just proceed with available information.
4. Generate the PRD
Produce a structured PRD with these sections. See PRD Structure below for detailed guidance on what each section should contain.
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 · 251 lines · 60 tokens per session scan A ca6670913878
write-spec is a skill published in the GitHub repository anthropics/knowledge-work-plugins (32,620 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 2,732 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 2026-09-05.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…