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/dhevenddra/forensic-deepdive/codebase-impact-analysisnpx skills add Dhevenddra/forensic-deepdive --skill codebase-impact-analysisgit clone --depth 1 https://github.com/Dhevenddra/forensic-deepdiveWhat 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 | $0.00121 | $0.00596 |
| Opus 5 | $0.00060 | $0.00298 |
| Sonnet 5 | $0.00024 | $0.00119 |
| Haiku 4.5 | $0.00012 | $0.00060 |
Grade A, and why
codebase-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 2d 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
Codebase impact analysis
Predict downstream effects of a change BEFORE making it. Never recommend a rename / removal / signature change without first surfacing callers and co-change neighbors.
When to use
- User proposes a rename, signature change, removal, deprecation, or split.
- Question shape: 'what depends on this', 'safe to delete X', 'where is Y called from', 'what breaks if I change Z'.
When NOT to use
- User is reading code to understand it →
codebase-exploring. - User is hunting a bug →
codebase-debugging. - User is restructuring with full knowledge of callers →
codebase-refactoring.
How to answer
- Always read
docs/codebase/AGENT_BRIEF.mdfirst — coupling rules ('if you touch X also touch Y') often pre-answer the question. - If MCP server is running (
forensic serve):impact(symbol, depth=3, direction='upstream')— every caller, depth-bucketed, with confidence per edge.context(symbol)— definition + callers + callees + parent + siblings + members + recent commits in one call.
- If MCP isn't running:
| Question shape | Artifact |
|---|---|
| 'Cross-file dependencies' | docs/codebase/HOTPATHS.md (Cross-file dependencies) |
| 'Coupling rules for this file' | docs/codebase/AGENT_BRIEF.md (Always rules) |
| 'Co-change cluster' | docs/codebase/HOTPATHS.md (Co-change clusters) |
Confidence discipline
The graph tags every edge EXTRACTED / INFERRED / AMBIGUOUS (DEC-015). When recommending a change, call out AMBIGUOUS callers explicitly — the resolver was unsure, so the human should double-check.
Citation rule
Cite docs/codebase/HOTPATHS.md:42 or the MCP tool output verbatim. Never say 'X is safe to delete' without showing the caller list (even when empty — 'no callers found in docs/codebase/HOTPATHS.md and impact() returned 0 upstream').
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.
- 2d ago First seen · 38 lines · 121 tokens per session scan A 3a24e7f17265
codebase-impact-analysis is a skill published in the GitHub repository Dhevenddra/forensic-deepdive (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 121 tokens to every session and 596 once invoked, about $0.0006 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
mistakes
List past mistakes engram has learned in this project — failures, regressions, broken assumptions. Use before starting a non-trivial change to surface relevant prior failures, or when debugging to check if this issue has been seen before.
query
Query engram's local knowledge graph for structural context — function calls, imports, type relationships, mistake history, ADRs. Use when the user asks "how does X work in this project", "what calls Y", "where is Z used", or any structural question that doesn't need file content.
chatcrystal-task-writeback
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through writetaskmemory or emit a structured memory candidate for later save.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
chatcrystal-task-recall
Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work. Use when the task is non-trivial, has repository or project context, and prior fixes, decisions, pitfalls, or reusable patterns may change the…
slm-graph
Index and query a codebase as a structural graph — build the code graph, trace blast radius of a change, find callers/callees/inheritors, semantic code search by meaning, assemble PR review context, and detect what changed since last index. Use when the user asks how code connects, what breaks if X changes, what calls…