Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/therealtinhtute-librarian
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/librarian
Tools it pre-approves 2
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
ReadBash
What's inside
- Skill name
librarian- Description
- GitHub code research via gh CLI, no cloning. Use to investigate external repos, find where a symbol is defined, or gather cited evidence and usage examples from GitHub.
- License
- MIT
- Compatibility
- Designed for Claude Code
- Allowed tools
- Read, Bash
- Metadata
- version: 1.0.0
- Instructions
- 108 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves any shell command
Files (5)
- SKILL.md
- citation-rules.md · references/
- examples.md · references/
- gh-patterns.md · references/
- output-format.md · references/
SKILL.md (first lines)
Lead with evidence and exact file locations.
<role>
Act as an evidence-first GitHub scout. Locate and cite exact GitHub code locations
using gh CLI. Cache files selectively, cite with line ranges, follow strict evidence
discipline. Never speculate beyond observed tool output.
</role>
<context>
## Scope
Does NOT handle: Local codebase research (use Explore agent or grep), git operations (use git
skill), model failover, subagent spawning, workspace isolation in /tmp
## When to Use
- Evidence from external GitHub code without cloning: symbol definitions, patterns, API usage examples
## Defer To Instead
- `git` — git operations, commits, PRs, branches
- `brainstorm` — comparing options after evidence is gathered
</context>
<instructions>
## Pre-flight Check
Before any GitHub search:
1. Run `gh --version` — if fails, report "gh CLI not installed. Install: https://cli.github.com"
2. Run `gh auth status` — if fails, report "gh not authenticated. Run: gh auth login"
If either check fails, stop and report the constraint.
## Core Strategy
Goal: smallest useful evidence set with exact citations.
1. **Search first** — use gh search before fetching files
2. **Cache selectively** — only files needed to prove your answer
3. **Cite precisely** — code claims need cached file + line range
4. **Stop when confident** — don't exhaust all possibilities
## Discovery Workflow
### 1. Understand the Query
- Symbol/text known? → Start with `gh search code`
- Repo known, paths unclear? → Use tree/contents API
- Path/metadata request? → Use search/tree output first
### 2. Search GitHub
Use the command templates in `references/gh-patterns.md`: code search with `--repo`/`--owner`/`--limit`, tree API for structure, contents API for listings; find symbol, explore structure, find examples, compare implementations.
### 3. Cache Files
Cache only files you need to cite, into `.zharness/cache/github/{owner}/{repo}/`, with the contents-API recipe in `references/gh-patterns.md`.
### 4. Read and Cite
Read cached files with line numbers. Cite as `.zharness/cache/github/owner/repo/path:lineStart-lineEnd`; keep snippets to 5-15 lines.
### 5. Write Findings
Report findings inline per `references/output-format.md`; save to `docs/research/{topic}.md` only when a plan will cite them.
## Citation Rules
Full rules and examples: `references/citation-rules.md`.
- **Code claims** cite a cached file with a line range; `gh search code` textMatches are not proof
- **Path claims** cite command output or `owner/repo:path`
- **Never speculate**: not observed in tool output → not a fact; nothing found → say "not found"
- **Partial evidence**: state what is confirmed and what remains uncertain
## Limits
At most 5 repos and 30 results per search; too broad → ask the user to narrow. 404/403 on a private repo → report the access constraint. Confirm the repo with `gh repo view` before deep-diving; cite only paths confirmed at HEAD. Cache, scope and anti-pattern details: `references/gh-patterns.md`.
</instructions>
<references>
Load as needed from `{baseDir}/references/`:
- `gh-patterns.md` — 7 known-good gh command templates; cache, scope limits, anti-patterns
- `citation-rules.md` — Evidence and citation discipline
- `output-format.md` — Markdown structure for findings
</references>
<closing>
After research: cite what was found (file:line), note what wasn't found and why, list cached files in `.zharness/cache/github/`, suggest next action (`brainstorm`, `git`, or narrower search).
</closing>From therealtinhtute/mono-harness, MIT.
More from therealtinhtute/mono-harness
- 0.624score
turbo-mono-platform
therealtinhtute
Full-stack TypeScript monorepo specialist: Turborepo, Next.js, Hono, tRPC, Drizzle, Postgres.
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
create-cli
therealtinhtute
Design CLI interfaces (commands, flags, I/O, errors, config) and produce implementation roadmaps with framework choice and shipping strategy.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
read
therealtinhtute
Search the web and fetch URLs or PDFs as clean Markdown via a privacy-first cascade (local, gh, TinyFish/Firecrawl/Exa, opt-in proxy).
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
think
therealtinhtute
Reason hard before building: attack premises, run named thinking lenses, compare real alternatives, give one verdict.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
git
therealtinhtute
Git operations with conventional commits.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
hunt
therealtinhtute
Find the root cause before any fix: build a red-capable repro loop, rank falsifiable hypotheses, prove, fix, sweep siblings.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
mono-mode
therealtinhtute
Entry router: match a task to one of twelve playbooks (feature, bug-fix, refactoring, perf, research, ship, ...) and run its skill steps as a todo list.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
retro
therealtinhtute
Session retrospective: evidence-cited, severity-ranked findings about the agent's environment, then one user-approved fix — a guard or a rerun-gated experiment.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
arena
therealtinhtute
Design bakeoff: sub-agents build one artifact several ways, a rubric picks the base, the best parts of the rest are grafted on.
SkillAFreshness: A★ 5Claude Code +9 - 0.618score
prompt-leverage
therealtinhtute
Strengthen a raw prompt into an execution-ready instruction set for Claude Code or another AI agent.
SkillAFreshness: A★ 5Claude Code +9 - 0.616score
watzup
therealtinhtute
Recap: read branch state, committed + uncommitted changes, handoff context, and artifact chain — then recommend the next action.
SkillAFreshness: A★ 5Claude Code +9 - 0.616score
check
therealtinhtute
Pre-commit and pre-merge gate.
SkillAFreshness: A★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 1
- Open issues
- 1
- Last commit (this folder)
- Oct 22, 2026 (6 days ago)
- Last release
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- MIT
- Repository
- github.com/therealtinhtute/mono-harness
- Website
- harness.tinhtute.me
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from therealtinhtute
- 0.624score
turbo-mono-platform
therealtinhtute
Full-stack TypeScript monorepo specialist: Turborepo, Next.js, Hono, tRPC, Drizzle, Postgres.
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
create-cli
therealtinhtute
Design CLI interfaces (commands, flags, I/O, errors, config) and produce implementation roadmaps with framework choice and shipping strategy.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
git
therealtinhtute
Git operations with conventional commits.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
think
therealtinhtute
Reason hard before building: attack premises, run named thinking lenses, compare real alternatives, give one verdict.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
hunt
therealtinhtute
Find the root cause before any fix: build a red-capable repro loop, rank falsifiable hypotheses, prove, fix, sweep siblings.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
read
therealtinhtute
Search the web and fetch URLs or PDFs as clean Markdown via a privacy-first cascade (local, gh, TinyFish/Firecrawl/Exa, opt-in proxy).
SkillAFreshness: A★ 5Claude Code +9
Cite this page
librarian skill. Agent Mart. https://agentmart.dev/skills/therealtinhtute-librarian (last updated 2026-10-24)