forensic-deepdive: Skill for Claude Code

.claude/skills/forensic-deepdive-update/SKILL.md

forensic-deepdive-update is a skill for Claude Code from Dhevenddra/forensic-deepdive. It costs 89 tokens per session (587 once invoked), scanned A, original, Apache-2.0.

A workflow for refreshing forensic-deepdive project-analysis files after the codebase has changed. These files document the code structure, important paths, history, and working model of a project.

In plain words
What is it for?
Use it when analysis artifacts are outdated or after significant changes, to rerun extraction and update files such as MAP.md, HOTPATHS.md, ARCHAEOLOGY.md, and AGENT_BRIEF.md.
Why use it?
It helps bring stale analysis back in line with the current code after many commits or a major refactor.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Dhevenddra/forensic-deepdive's own configuration. It tells Claude Code how to work on forensic-deepdive itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything forensic-deepdive configures →

Part of the forensic-deepdive plugin — 3 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to Dhevenddra/forensic-deepdive. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Dhevenddra/forensic-deepdive/main/.claude/skills/forensic-deepdive-update/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Dhevenddra/forensic-deepdive

Made for: Claude Code.

Or install forensic-deepdive, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote 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.

agentmods badge for forensic-deepdive-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/dhevenddra/forensic-deepdive/forensic-deepdive-update.svg)](https://agentmods.dev/skills/dhevenddra/forensic-deepdive/forensic-deepdive-update)
Your own site
<a href="https://agentmods.dev/skills/dhevenddra/forensic-deepdive/forensic-deepdive-update"><img src="https://agentmods.dev/badge/skills/dhevenddra/forensic-deepdive/forensic-deepdive-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 587 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.00587
Opus 5 $0.00044 $0.00293
Sonnet 5 $0.00018 $0.00117
Haiku 4.5 $0.00009 $0.00059

Measured 8d ago against content hash fb1c94b2023b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

forensic-deepdive-update 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 8d 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.

.claude/skills/forensic-deepdive-update/SKILL.md · 49 lines

What it actually says

Forensic Deep-Dive — Update

Incrementally refresh artifacts. In v0.1 this is a stub that calls forensic extract --force (full re-run). In v0.2 it becomes truly incremental.

When to use

  • Artifacts >7 days old AND >50 commits behind HEAD.
  • User explicitly asks to refresh.
  • Major refactor just landed.

When NOT to use

  • First time on this repo → use forensic-deepdive-extract.
  • Just answering a question → use forensic-deepdive-query.
  • Artifacts are fresh (<7 days, <50 commits behind) → no refresh needed.

How to run

forensic update . --since=last-extract

This (in v0.2):

  1. Reads .forensic-deepdive/cache/last_run.json for previous commit SHA.
  2. Computes changed files via git diff --name-only <sha>..HEAD.
  3. Re-parses only changed files (Tree-sitter), incrementally updates the symbol graph.
  4. Re-runs PageRank (under 1s for 100k symbols).
  5. Per-artifact staleness:
    • MAP.md if any top-50 PageRank node changed.
    • HOTPATHS.md if any active ast-grep query's match-set changed.
    • ARCHAEOLOGY.md appends new commits/PRs/issues since last run.
    • MENTAL_MODEL.md skipped unless --force or ≥20% symbol churn.
    • AGENT_BRIEF.md regen if dependency manifest, CI workflow, or top-10 file changed.
  6. Updates the <!-- generated --> header on each touched artifact.

In v0.1, this calls forensic extract --force (full re-run). Document the limitation.

Caveats

  • Major directory restructure → prefer full forensic extract --force.
  • New subsystem merged → use --force-mental-model to refresh that one artifact.

What to report back

  • Which artifacts were refreshed and which were skipped (with reason).
  • Diff summary if non-trivial: "MAP.md added 3 new top-50 nodes: A, B, C."
  • Cost report from .forensic-deepdive/last_run.json.
Changes

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.

  1. 8d ago First seen · 49 lines · 89 tokens per session scan A fb1c94b2023b

Subscribe to this mod's changes

forensic-deepdive-update is a skill published in the GitHub repository Dhevenddra/forensic-deepdive (2 stars, last pushed 22d ago), licensed Apache-2.0. It adds 89 tokens to every session and 587 once invoked, about $0.0004 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.