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/adamfaik/claude-code-pm-starter/setup-workspacenpx skills add adamfaik/claude-code-pm-starter --skill setup-workspacegit clone --depth 1 https://github.com/adamfaik/claude-code-pm-starterWrote 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/adamfaik/claude-code-pm-starter/setup-workspace)<a href="https://agentmods.dev/skills/adamfaik/claude-code-pm-starter/setup-workspace"><img src="https://agentmods.dev/badge/skills/adamfaik/claude-code-pm-starter/setup-workspace.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 | $0.00057 | $0.00535 |
| Opus 5 | $0.00028 | $0.00267 |
| Sonnet 5 | $0.00011 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
setup-workspace 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup workspace
Turn the template files into the user's own workspace through a short interview. The user answers in plain language; you do all the writing.
How to run the interview
- Ask in rounds, one topic at a time, in this order: company, product, users, working and writing preferences, current projects. A few questions per round, not a wall of them.
- Plain questions a busy person can answer from memory: "What does your company sell, and to whom?", "Who do you picture when you make product decisions?", "What's a correction you find yourself giving on every AI draft?"
- Accept short answers and draft from them. Show what you wrote and ask for a yes or a fix before moving to the next topic. The user's words beat template language; keep their phrasing where it's clear.
- Skipping is fine. If the user doesn't know or doesn't care about a section, leave the template placeholder in place and move on. An honest placeholder beats invented content.
What to fill
CLAUDE.md— replace the first line with who the user actually is (role, company). Keep the file short; it's a map, not a manual.context/company.md— what the company does, how it's organized, competitors, vocabulary.context/product.md— what the product is, positioning, current strategy, key metrics (names and where they live, not live numbers).context/users.md— segments, primary persona, strongest findings.context/preferences.md— writing preferences and working preferences in the user's own words. Replace the template examples with theirs; delete examples they don't want.projects/example-project/— ask for the user's most active real project. Rename the folder to a short slug of it, fillbrief.mdfrom what they tell you, and seedtasks.mdwith their current next steps. If they'd rather start empty, leave the example in place.
Finish
Show a short summary of every file you touched. Then suggest one concrete next move: give the workspace a real task, for example /status-update or a first draft the user owes someone. Remind them once: when they correct something you got wrong, /file-feedback makes the correction permanent.
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 · 29 lines · 57 tokens per session scan A f2ae138cdf05
setup-workspace is a skill published in the GitHub repository adamfaik/claude-code-pm-starter (10 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 535 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…