gtapps/hermit-brain
plugins/claude-code-hermit/skills/hermit-brain/SKILL.md
Show fragile zones, stale accepted proposals, and recent learnings drawn from session history, proposals, and reflect output. Activates on messages like 'what's stuck', 'any fragile zones', 'show me what's blocked', 'recent learnings', 'hermit brain', 'what have you learned lately', 'where are the weak spots'.
$ install --global
skillsauthnpx skillsauth add gtapps/claude-code-hermit hermit-brainInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 19, 2026, 5:47 AM52.0s1 file scanned
SKILL.md
- name:
- hermit-brain
- description:
- Show fragile zones, stale accepted proposals, and recent learnings drawn from session history, proposals, and reflect output. Activates on messages like 'what's stuck', 'any fragile zones', 'show me what's blocked', 'recent learnings', 'hermit brain', 'what have you learned lately', 'where are the weak spots'.
Hermit Brain
Synthesize a compact analytical snapshot of the hermit's current knowledge state: where things are fragile, which accepted proposals have stalled, and what has been recently learned.
Step 0 — Channel reply
If this skill was invoked from a channel-arrived message (the inbound prompt contains a <channel source="..."> tag), reply via that channel's reply tool. Otherwise emit to conversation.
Scope
Read the following (gracefully skip any file that doesn't exist):
.claude-code-hermit/sessions/SHELL.md— current session context, tags, blockers.claude-code-hermit/sessions/S-*-REPORT.md— glob all, sort descending by filename, read the 5 most recent; parsestatus,tags,proposals_createdfrontmatter.claude-code-hermit/proposals/PROP-*.md— glob all; for each readid,title,status,accepted_date,resolved_date,tagsfrom frontmatter.claude-code-hermit/state/reflection-state.json—last_reflection,queue(pending micro-proposals and reflect candidates)
Analysis
Fragile zones: From the last 5 session reports, gather the tags array from sessions with status: partial or status: blocked. Also gather tags from proposals with status: dismissed or status: blocked. Surface the top 2–3 tag clusters that appear repeatedly across fragile outcomes. If no blocked/partial sessions exist: "No fragile zones detected."
Stale proposals: From proposals, find those with status: accepted and resolved_date absent or null. Sort by accepted_date ascending (oldest first). Show up to 3. Compute days open = today minus accepted_date. If none: "No accepted proposals awaiting resolution."
Recent learnings: From reflection-state.json, read queue entries with status: accepted or status: pending and surface the most recent 3 question/observation fields. If the queue is empty or absent, scan the current SHELL.md Progress Log for notable Findings entries (lines beginning with - under ## Findings). Surface top 3. If nothing: "No recent learnings — reflect hasn't run yet."
Output
Reply in ≤1500 chars. Use exactly this section structure:
### Fragile zones
- [tag or theme]: [one-line reason]
(or: No fragile zones detected — no blocked/partial sessions yet.)
### Stale proposals
- PROP-NNN: [title] (accepted N days ago)
(or: No accepted proposals awaiting resolution.)
### Recent learnings
- [learning]
(or: No recent learnings — reflect hasn't run yet.)
Omit sections that have no data rather than showing a heading with an empty body. Keep each bullet to one line.
Related Skills
gtapps/session-start
data-ai
VerifiedTrustedCommunity
Initializes or resumes a work session. Loads context from OPERATOR.md and SHELL.md, orients the agent, and establishes what to work on. Use at the beginning of every work session.
62SKILL.mdUpdated Apr 27, 2026
gtapps/hermit-evolve
tools
VerifiedTrustedCommunity
Evolves hermit configuration and templates after a plugin update. Detects version gaps, presents new features, walks through new settings. Run after updating the plugin.
62SKILL.mdUpdated Apr 27, 2026
gtapps/hatch
testing
VerifiedTrustedCommunity
Initializes the autonomous agent in the current project. Creates the state directory, templates, OPERATOR.md, and config.json. Appends session discipline to CLAUDE.md. Detects installed hermits. Run once per project, like git init.
62SKILL.mdUpdated Apr 27, 2026
gtapps/docker-setup
tools
VerifiedTrustedCommunity
Generates Docker scaffolding and walks the operator through the full deployment — token setup, build, start, MCP plugin configuration, workspace trust, and verification. Offers to back up and overwrite existing Docker files. Run after /hatch.
62SKILL.mdUpdated Apr 27, 2026