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/bostonorange/claude-code-framework/impactnpx skills add BostonOrange/claude-code-framework --skill impactgit clone --depth 1 https://github.com/BostonOrange/claude-code-frameworkWhat 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 | $0.00068 | $0.01190 |
| Opus 5 | $0.00034 | $0.00595 |
| Sonnet 5 | $0.00014 | $0.00238 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade B, and why
impact 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 yesterday.
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.
description: On-demand precise impact analysis for a symbol or file before changing it. Spawns impact-analyzer to grep callers, classify the cascade (direct/indirect/test-only), and produce a confidence-scored report. Di How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impact — On-Demand Cascade Analysis
Before making a confident-but-wrong change to a function, class, or file, run /impact to see what would break.
/impact answers questions like "if I change the return type of requireAuth, what breaks?" — without you having to grep callers, read each one, and reason about cascades by hand. Output is a structured report at .claude/state/impact-<hash>.md plus a short summary.
This complements .claude/state/architecture.md:
- architecture.md is the broad map (module boundaries, dependency direction, top-10 hotspots) refreshed by
/improveeach session /impact <symbol>is the focused drill-down for a specific change you're about to make
Usage
/impact <file> analyze every exported symbol in the file
/impact <file>:<symbol> analyze just that symbol
/impact <symbol> bare symbol; spawns analyzer to find definition first
/impact --refresh <target> ignore cache; re-run analysis
Examples:
/impact lib/auth/middleware.ts
/impact lib/auth/middleware.ts:requireAuth
/impact requireAuth
/impact AccountTriggerHandler.cls:beforeInsert # Apex
Process
Phase 1: Spawn impact-analyzer
Run impact analysis on <target>. Locate the definition, find direct callers,
classify references (direct/type/test), trace second-order public callers
(depth=2 max), score confidence, write the report to .claude/state/impact-<hash>.md.
End with the surface summary.
The agent is read-only by tool restriction (Read, Glob, Grep, Bash — no Edit/Write). Its only filesystem write is the report file.
Phase 2: Surface to user
Read the agent's summary output. Show:
- Total references + breakdown (direct / type / test)
- Confidence level + top caveat
- Top 3 most-impacted files
- Recommendation one-liner
- Path to the full report
Phase 3: Hand-off
If the user is iterating on a change:
- "Confidence is high — proceed; the test suite at
<paths>should catch regressions" - "Confidence is medium — review the second-order callers in
.claude/state/impact-<hash>.mdbefore merging" - "Confidence is low — string-keyed lookups detected; grep can't see them all. Consider running tests in addition"
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.
- yesterday First seen · 103 lines · 68 tokens per session scan B 958c27f34ab6
impact is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,190 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…