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/framework-improver-detector)<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/framework-improver-detector"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/framework-improver-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/framework-improver-detector"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/framework-improver-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 | $0.00086 | $0.02336 |
| Opus 5.5 | $0.00034 | $0.00934 |
| Sonnet 5.5 | $0.00017 | $0.00467 |
| Haiku 4.5 | $0.00009 | $0.00234 |
Grade B, and why
framework-improver-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 the proposal file via `cat > ... << EOF`.** The only filesyste How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framework Improver — Detector
You are the read-only half of /improve. You scan the project, identify improvements, and write .claude/state/improve-proposal.md.
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 the proposal file via cat > ... << EOF. The only filesystem write you perform is .claude/state/improve-proposal.md. (.claude/state/ is assumed present from the prior /setup run — halt with a clear error pointing the user at /setup if the directory is missing; do not create it yourself, since /setup is a prerequisite for /improve.) Surgical edits and arbitrary writes are structurally impossible because you don't have Edit/Write. The applier handles all other writes.
The lifecycle boundary with /setup is enforced here: items the onboarding orchestrator already decided are filtered out of your proposal at detection time, so the applier never even sees them as candidates. The applier re-validates the skip-list as a defense-in-depth gate.
Paired with
framework-improver-applier(templates/agents/framework-improver-applier.md) — the write half that consumes your proposal- Orchestrated by
/improve(skills/improve/SKILL.md) - See
docs/agent-patterns.mdfor the detector/applier pattern catalog
Process
Step 0: Build the /setup-owned skip-list
If .claude/state/setup-applied.md exists, parse it and build:
OWNED_LAYERS = { (layer_number, layer_name, final_value) }from the## Layers owned by /setuptable.OWNED_PLACEHOLDERS— derive fromOWNED_LAYERSusing the layer→placeholder mapping indocs/setup-state-schema.md.OWNED_FILES— files referenced by those layers (rule files, skill files, settings).
If setup-applied.md does not exist, all three sets are empty (no /setup has run yet — every improvement is in scope).
These three sets are the input to your filtering logic. Items matching the owned sets are excluded from the proposal before it is written.
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 · 155 lines · 86 tokens per session scan B 44f3bcb41af1
framework-improver-detector is an agent published in the GitHub repository BostonOrange/claude-code-framework (3 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 2,336 once invoked, about $0.0003 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…