Handles "deep dive: <slug>" follow-up requests. Resolves the referenced item from recent briefs, does targeted web research on its primary source, and delivers a focused ~10-15 line analysis via the configured channel. General follow-up by default; a security variant when the item is security-tagged. Invoke with /hermitd-feed:deep-dive <slug>.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Deep Dive
Deliver a focused follow-up analysis for a topic slug referenced in a recent brief.
## Input
The argument is the slug from the brief CTA (e.g., `local-first-sync`, `apex-one-zero-day`).
## Steps
1. **Resolve the item.** Glob `.hermit/briefs/` for files from the last 14 days (sort by
date, newest first). Scan each for the slug (case-insensitive substring match against the brief body).
Extract the surrounding paragraph — the item's headline, description, any URL, and its category/tags.
2. **Web research.** Using the URL and headline from the brief (if found), run 1–2 targeted WebFetch calls
to reach the primary source. If no URL is available, use the slug as a search hint. Collect what the
analysis template needs: what happened, key facts/dates, current status, and (for security items) CVE/CVSS,
affected versions, exploitation status, patch status.
3. **Write the analysis.** ≤10–15 lines. Pick the template by the briefed item's nature:
**Default (general follow-up)** — for any non-security item:
```
**Deep dive: <slug>**
**What happened:** One–two sentences on the development and its context.
…
The line at the top of this page pins the label git:20261002.2f2da1b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (3868 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
gtapps/hermitd · 82 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_s4jhk3tpaapldq3d
GET https://markdownregistry.com/api/v1/resolve?ref=gtapps/hermitd/deep-dive
GET https://markdownregistry.com/api/v1/blob/36aabe2b6114c2394fc899619350c6800a6a0d48aedbd0eb6127d826c44b4dcf
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
gtapps/hermitd · .agents/skills/bump-core-req/SKILL.md · Updates the minimum core version requirement for a fleet plugin in all three canonical places: `required_core_version`…
gtapps/hermitd · .agents/skills/claude-harness-canary/SKILL.md · Run the minimum current-Claude compatibility canary for hermitd by driving real interactive Claude Code instances in…
gtapps/hermitd · .agents/skills/commit/SKILL.md · Changelog and commit — lightweight motion for day-to-day plugin dev work in the monorepo. One commit per plugin scope…
gtapps/hermitd · .agents/skills/docs-drift/SKILL.md · Documentation-drift audit for this plugin monorepo. Audit either each scoped plugin's unreleased changelog claims or…
gtapps/hermitd · .agents/skills/downstream-impact/SKILL.md · Explain in plain language what a fix, feature, PR, or plan will actually change for downstream hermits and the…
gtapps/hermitd · .agents/skills/fleet-release/SKILL.md · Use this skill whenever the user wants to release, ship, prep, or cut versions for two or more plugins together on the…
gtapps/hermitd · .agents/skills/pipeline-digest/SKILL.md · Daily release-pipeline digest with a change gate — reports which plugins are pending release, whether main's CI is…
gtapps/hermitd · .agents/skills/pre-release-review/SKILL.md · Run the pre-release gate for this multi-plugin monorepo: establish each plugin's release boundary from its last…
gtapps/hermitd · .agents/skills/pricing-refresh/SKILL.md · Refresh or verify the hermit cost rate table against Anthropic's live pricing. Use when the operator says "refresh…
gtapps/hermitd · .agents/skills/release-status/SKILL.md · Use this skill to answer "what's ready to ship?", "where does the release pipeline stand?", "any plugins awaiting…
gtapps/hermitd · .agents/skills/release/SKILL.md · Bump a plugin's version, write a detailed changelog entry for the upgrade skill to consume, and commit+push. Takes a…
gtapps/hermitd · .agents/skills/routine-test-ping/SKILL.md · Proof-of-life for the routine monitor. Appends one timestamped line to SHELL.md under Monitoring and stops. Fired by…
zereight/gitlab-mcp · .github/skills/deep-dive/SKILL.md · 2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive…
zaxbyhub/opencode-swarm · .opencode/skills/deep-dive/SKILL.md · Full execution protocol for MODE: DEEP_DIVE — read-only codebase audit with parallel explorer waves, 2 independent…
zaxbyhub/opencode-swarm · .claude/skills/deep-dive/SKILL.md · Full execution protocol for MODE: DEEP_DIVE — read-only codebase audit with parallel explorer waves, 2 independent…
fabioc-aloha/alex_skill_mall · plugins/academic-research/deep-dive/skills/deep-dive/SKILL.md · Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No…