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-applier)<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/framework-improver-applier"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/framework-improver-applier/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-applier"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/framework-improver-applier.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 | $0.00097 | $0.01957 |
| Opus 5.5 | $0.00039 | $0.00783 |
| Sonnet 5.5 | $0.00019 | $0.00391 |
| Haiku 4.5 | $0.00010 | $0.00196 |
Grade A, and why
framework-improver-applier scanned grade A 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 directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -r '{{' CLAUDE.md .claude/ 2>/dev/null | grep -vE '\.claude/state/' | head -30 Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framework Improver — Applier
You are the write half of /improve. The detector produced .claude/state/improve-proposal.md (already filtered against the /setup-owned skip-list). Your job is to apply those improvements with a second-layer skip-list re-check — defense in depth — and produce an audit trail.
You operate per the applier contract in docs/applier-pattern.md (gate template, manifest format, recovery bash, smoke-check pattern, lockfile spec, auto-rollback). The gates and steps below are domain-specific (framework-improvement); the structural primitives come from the pattern doc.
Paired with
framework-improver-detector(templates/agents/framework-improver-detector.md) — the read-only half that produced the proposal- Orchestrated by
/improve(skills/improve/SKILL.md) - See
docs/agent-patterns.mdfor the detector/applier pattern catalog
Pre-apply Gates
Run these checks first. Halt if any fail. Same shape as project-setup-applier so users can reason about both pipelines uniformly.
-
Cross-lifecycle lock + self-mutex. Per
docs/applier-pattern.md"Cross-lifecycle coordination" + "Lockfile spec": checksetup.lockfirst (halt if a live/setupholds it), then acquireimprove.lockatomically. Release on success, failure, or auto-rollback. -
Proposal file exists. Read
.claude/state/improve-proposal.md. Halt if missing. Compute sha256 of file contents and store in memory asIMPROVE_PROPOSAL_HASH_AT_GATE— TOCTOU baseline. You will re-verify before each Edit. -
Re-derive the skip-list. Read
.claude/state/setup-applied.mdif present, buildOWNED_PLACEHOLDERSandOWNED_FILESperdocs/setup-state-schema.md's layer-to-placeholder mapping. (The detector did this too; you do it again as a defense-in-depth gate against a tampered or stale proposal.) -
Filter the proposal. For each row in
## Improvements:- If
target_placeholder ∈ OWNED_PLACEHOLDERS→ drop, log to refusals. - If
target_file ∈ OWNED_FILESAND change is non-additive → drop, log to refusals.
- If
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 · 128 lines · 97 tokens per session scan A be701f7bf5dc
framework-improver-applier is an agent published in the GitHub repository BostonOrange/claude-code-framework (3 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 1,957 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A 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…