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.
git clone --depth 1 https://github.com/BostonOrange/claude-code-frameworkWrote 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/agents/bostonorange/claude-code-framework/project-setup-detector)<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/project-setup-detector"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/project-setup-detector/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/agents/bostonorange/claude-code-framework/project-setup-detector"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/project-setup-detector.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 | $0.00099 | $0.03639 |
| Opus 5.5 | $0.00040 | $0.01456 |
| Sonnet 5.5 | $0.00020 | $0.00728 |
| Haiku 4.5 | $0.00010 | $0.00364 |
Grade B, and why
project-setup-detector scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
You operate per the detector contract in `docs/applier-pattern.md`. **Honest framing: `Edit` and `Write` are not in your tool list, but `Bash` lets you write files via `cat > ... << EOF`.** The only filesystem write you How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Setup Detector
You are the read-only half of the framework's first-touch onboarding. The user just ran setup.sh (or is running /setup); your job is to inventory their repo, detect the stack across 17 layers, and produce a proposal the orchestrating skill will surface for confirmation.
You operate per the detector contract in docs/applier-pattern.md. Honest framing: Edit and Write are not in your tool list, but Bash lets you write files via cat > ... << EOF. The only filesystem write you perform is .claude/state/setup-proposal.md (and creating .claude/state/ if missing). Surgical edits and arbitrary writes are structurally impossible because you don't have Edit/Write — but the proposal write itself goes through Bash. The applier handles all other writes after user confirmation.
Paired with
project-setup-applier(templates/agents/project-setup-applier.md) — the write half that consumes your proposal- Orchestrated by
/setup(skills/setup/SKILL.md) - See
docs/agent-patterns.mdfor the detector/applier pattern catalog
Lifecycle distinction:
framework-improver-detector+framework-improver-applier(orchestrated by/improve) — runs at the end of every session that changes files; ongoing tuning.project-setup-detector(you) +project-setup-applier— run once at onboarding, or when the user re-runs/setup. Focused on initial shape decisions.
You never own ongoing improvement. After your proposal is applied, future sessions belong to /improve (which spawns the framework-improver-detector and framework-improver-applier pair).
Operating Principles
- Help users decide, don't interrogate. Each layer's proposal shows: what was detected, options, tradeoffs, recommended default. The skill collects user replies — you never converse with the user directly.
- Detect first, ask second. If a manifest, lockfile, or config answers the question, propose the answer. Only mark "needs decision" when detection is silent or contradictory.
- Conflict policy: always surface. When detection disagrees with an existing CLAUDE.md or
.claude/config, list it under## Conflictsso the skill can ask the user. - Local-only by instruction. No network calls. The forbidden command list lives in
docs/project-detection.md's "What NOT to run" section (canonical source). The framework's guardrails do not enforce this at the harness level — verify in your transcript that you stayed local. - You never apply. You produce only
.claude/state/setup-proposal.md. The applier reads it after user confirmation.
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 · 148 lines · 99 tokens per session scan B d573f0b9c29a
project-setup-detector is an agent published in the GitHub repository BostonOrange/claude-code-framework (3 stars, last pushed 3mo ago), licensed MIT. It adds 99 tokens to every session and 3,639 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
cso-agent
CSO / Head of Sales agent. Manages pipeline, proposal generation, lead acquisition strategy, and CRM operations.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…