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 richfrem/agent-plugins-skills --skill project-setupgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/project-setup)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/project-setup"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/project-setup/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/richfrem/agent-plugins-skills/project-setup"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/project-setup.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 | $0.00041 | $0.00546 |
| Opus 5.5 | $0.00016 | $0.00218 |
| Sonnet 5.5 | $0.00008 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
project-setup 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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Project Setup
Configure the selected project and establish one reusable capability baseline.
Contents
Constraints
Require plugin installation, os-control-init and os-control-health before declaring readiness. Reuse confirmed answers; ask one question at a time for missing information. Installed alone never counts as provider access or project authorization. Never store credentials, tokens, prompts or raw provider output in the profile. Project setup does not authorize reviewer dispatch. Do not dispatch an internal reviewer without an authorized runtime/model/effort choice at the applicable review gate.
Quick start
Identify the caller's project root and existing profile before asking new questions.
Read the capability interview and
profile contract. Load the project's
profile with the bundled scripts/capability_profile.py load_profile interface.
Workflow
- Verify prerequisites; report exact remediation when missing.
- Establish or refresh the baseline; reuse a ready profile and ask only about changes.
- Delegate catalog authority to update-cli-models when refresh is actually needed; this skill does not duplicate model catalog policy or refresh models at later gates.
- Follow configuration workflow.
- Present the concrete setup plan; use existing authorization or obtain approval before writing the selected project's configuration files.
- Validate and persist the profile, then report configuration paths and readiness.
Verification
Use write_profile/load_profile to verify context/agent-capability-profile.json
in the selected project. Later pipeline stages must read it rather than repeat setup.
context/memory/environment.md is a human-readable fallback, not another preference store.
Check configuration syntax, selected runtime requirements and unavailable-provider guidance.
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 806 B
- evals/results.tsv 34 B
- references/acceptance-criteria.md 42 B
- references/antigravity-directory-spec.md 49 B
- references/capability-profile-contract.md 50 B
- references/claude-directory-spec.md 44 B
- references/claude-settings-schema.md 45 B
- references/gemini-cli-commands.md 42 B
- references/project-capability-baseline.md 50 B
- references/project-configuration-workflow.md 53 B
- scripts/capability_profile.py 38 B runs code
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.
- 5d ago Changed b95cb9ac71ba
- 18d ago Changed · -102 lines · -19 tokens per session ca929f65acd6
- 1mo ago Changed · +79 lines 982303b80b8b
- 1mo ago Changed · +35 lines 007078002a57
- 1mo ago First seen · 49 lines · 60 tokens per session scan A 98770ddd39a5
project-setup is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 546 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
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
factory-handoff
Hand one exact agent-ready ticket to the central Factory runtime over the configured SSH forced-command boundary. Use when an operator asks to hand off an existing ticket or a prose request instead of implementing it in the current session.
ticket-spec
Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
review-my-team
Review a connected Paperclip team's agents, tasks, blockers and pending approvals when the user asks for a team summary or what needs attention.
ap-independent-checker
Independently review the exact result and run its real checks in one context, using isolated resources and without changing the deliverable.