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/cdeust/ai-architect-mcp-codebase/impact-analysisnpx skills add cdeust/ai-architect-mcp-codebase --skill impact-analysisgit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWrote 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/cdeust/ai-architect-mcp-codebase/impact-analysis)<a href="https://agentmods.dev/skills/cdeust/ai-architect-mcp-codebase/impact-analysis"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp-codebase/impact-analysis.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00366 |
| Opus 5 | $0.00028 | $0.00183 |
| Sonnet 5 | $0.00011 | $0.00073 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
impact-analysis 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 4d 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.
What it actually says
Impact Analysis
Use the eight-tool core profile. Treat graph results as a lower bound wherever the tool reports heuristic resolution, dynamic dispatch, or coverage gaps.
Workflow
- Call
health_check. Build or refresh the graph withanalyze_codebase, and keep the exact returnedgraph_path. - If an actual unified diff or base/head refs exist, call
detect_changes. Do not invent a diff for a proposal that has not been implemented. - Use
search_codebaseto resolve every proposed or changed symbol to an exact qualified name. Confirm important targets withget_symbolorget_context. - Call
get_impactfor each target. Page callers throughnext_offset. Treat importers, users, and implementors as capped summaries; usequery_graphwith an explicitORDER BYwhen a complete paged list matters. - Call
query_graphwithgraph="missed". Inspect flagged files or ranges before making a negative claim about callers, dependencies, or test coverage. - Follow high-risk dependents with
get_contextorget_symbol. Use sibling graphs only when the user supplies or authorizes those graph paths.
Deliverable
Separate direct graph evidence from inference. Report affected symbols, callers and dependency types, communities, execution processes, co-change hints, coverage gaps, and unverified risks. Preserve the tool's epistemic qualifier instead of upgrading a lower-bound result into a completeness claim.
What ships with it
1 file 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.
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.
- 4d ago First seen · 23 lines · 55 tokens per session scan A a0052f3b63e9
impact-analysis is a skill published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 366 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
brooks-audit
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized…
brooks-review
PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on twelve classic engineering books. Triggers when: user asks to review code, check a PR, shares a diff or pastes code asking "does this look right?" / "any issues…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
cortex-takeoff
Create or resume a session takeoff baton — a curated, ephemeral, git-ignored hand-off note that lets the next Claude session continue a long-running task. A repo can hold several batons at once, one per work line (topic). Use when the user says "交接", "takeoff", "交棒", "context 快滿了交接給下個 session", "hand off to next…