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.
curl -O https://raw.githubusercontent.com/Dhevenddra/forensic-deepdive/main/.claude/skills/forensic-deepdive-update/SKILL.mdgit clone --depth 1 https://github.com/Dhevenddra/forensic-deepdiveWrote 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/dhevenddra/forensic-deepdive/forensic-deepdive-update)<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>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 5.1 | $0.00089 | $0.00587 |
| Opus 5 | $0.00044 | $0.00293 |
| Sonnet 5 | $0.00018 | $0.00117 |
| Haiku 4.5 | $0.00009 | $0.00059 |
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.
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):
- Reads
.forensic-deepdive/cache/last_run.jsonfor previous commit SHA. - Computes changed files via
git diff --name-only <sha>..HEAD. - Re-parses only changed files (Tree-sitter), incrementally updates the symbol graph.
- Re-runs PageRank (under 1s for 100k symbols).
- 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
--forceor ≥20% symbol churn. - AGENT_BRIEF.md regen if dependency manifest, CI workflow, or top-10 file changed.
- 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-modelto 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.
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.
- 8d ago First seen · 49 lines · 89 tokens per session scan A fb1c94b2023b
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.
Other skills, from other repositories
revibe
Analyze any codebase — architecture, patterns, diagrams, agent context. Understand repos in minutes, not hours.
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.