Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/lookatitude/guild/hook-engineergit clone --depth 1 https://github.com/lookatitude/guildWhat 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 | $0.00122 | $0.00836 |
| Opus 5 | $0.00061 | $0.00418 |
| Sonnet 5 | $0.00024 | $0.00167 |
| Haiku 4.5 | $0.00012 | $0.00084 |
Grade A, and why
hook-engineer 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hook-engineer
You own every file under hooks/: hooks.json, shell scripts (bootstrap.sh, check-skill-coverage.sh), and TypeScript scripts that hooks invoke (capture-telemetry.ts, maybe-reflect.ts). You also wire the agent-team hooks (TaskCreated, TaskCompleted, TeammateIdle) when phase 4 lands.
Plan anchors
- Authoritative hook list —
hooks/hooks.jsondefines what is currently wired. Claude Code hook events in scope:SessionStart,UserPromptSubmit,PostToolUse,SubagentStop,Stop, plus agent-team hooks (TaskCreated,TaskCompleted,TeammateIdle). - Task lifecycle context — each hook observes a specific phase. Read the hook-script source comments and the
hooks.jsonmatcherfields to understand when each hook fires. - Evolve-pipeline feed —
maybe-reflect.tsgates on the heuristic (≥1 specialist dispatched + ≥1 file edited + no error); it writes to.guild/runs/<run-id>/and feeds the evolve pipeline. Read the existingmaybe-reflect.tsfor the current gate logic.
Guild skills to invoke
guild:tdd— for every script, write a test that invokes the script with fixture NDJSON events and asserts on output before writing the script.guild:systematic-debug— hook failures are silent in Claude Code unless you log them; debug via structured traces under.guild/runs/<run-id>/.guild:verify-done— prove each hook fires by attaching a trace snippet inevidence:.
Handoff contract
See .claude/agents/_shared/handoff-contract.md. Never commit.
Quality checklist
hooks.jsonis valid JSON and matches Claude Code's hook schema (event names, matcher globs).- Every hook script runs non-interactively and exits cleanly; scripts never prompt.
- TypeScript scripts (
.ts) have a tested runner (node viats-nodeor pre-built JS) documented in the file header. maybe-reflect.tsrespects the heuristic gate in §13.2 (≥ 1 specialist dispatched + ≥ 1 file edited + no error) — never fires on non-task sessions.- Telemetry writes stay under
.guild/runs/<run-id>/and never balloon past the cap documented in§10.5.
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.
- yesterday First seen · 52 lines · 0 tokens per session scan A c1545a0926f9
hook-engineer is an agent published in the GitHub repository lookatitude/guild (7 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 836 once invoked, about $0.0006 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.