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-debuggingnpx skills add Dhevenddra/forensic-deepdive --skill codebase-debugginggit 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 | $0.00117 | $0.00516 |
| Opus 5 | $0.00059 | $0.00258 |
| Sonnet 5 | $0.00023 | $0.00103 |
| Haiku 4.5 | $0.00012 | $0.00052 |
Grade A, and why
codebase-debugging 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 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.
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 debugging
Triangulate a bug to its likely region without re-reading the whole repo.
When to use
- User reports an error / regression / flake / unexpected output.
- Question shape: 'why is X broken', 'where does this exception originate', 'what changed that could cause this', 'this used to work'.
When NOT to use
- User is orienting / learning, not fixing →
codebase-exploring. - User is planning a refactor →
codebase-refactoring. - Question is about correctness of a single function → just read it.
How to answer
- Always read
docs/codebase/AGENT_BRIEF.mdfirst — the never/always rules often pin the load-bearing call site. - Match the question shape:
| Question shape | Artifact |
|---|---|
| 'What are the hot spots / where is most activity' | docs/codebase/HOTPATHS.md (Dependency hot spots) |
| 'What changed recently around X' | docs/codebase/ARCHAEOLOGY.md (Recent commits, churn) |
| 'What's the defect-proximity neighborhood' | docs/codebase/ARCHAEOLOGY.md |
| 'What co-changes with this file' | docs/codebase/HOTPATHS.md (Co-change clusters) |
- If
forensic serveis running, callarchaeology(file_or_symbol)for the full git-history view in one call — recent commits, dominant author, defect proximity, co-change cluster.
Citation rule
Cite docs/codebase/HOTPATHS.md:42 or docs/codebase/ARCHAEOLOGY.md:78. If a graph-mode HOTPATHS shows AMBIGUOUS-confidence edges around the suspect symbol, surface that — agents and humans both need to know the resolver wasn't sure.
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 · 35 lines · 117 tokens per session scan A c0ff486bc4b1
codebase-debugging is a skill published in the GitHub repository Dhevenddra/forensic-deepdive (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 117 tokens to every session and 516 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-recall
Search and retrieve facts, decisions, and past context from SuperLocalMemory. Use when the user asks to recall, find, search, or "what did we decide/say about X". Triggers multi-channel semantic retrieval with reranking; always call before storing anything new.