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 skills/monkilabs/opencastle/agent-hooksnpx skills add monkilabs/opencastle --skill agent-hooksgit clone --depth 1 https://github.com/monkilabs/opencastleWhat 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 | $0.00886 |
| Opus 5 | $0.00061 | $0.00443 |
| Sonnet 5 | $0.00024 | $0.00177 |
| Haiku 4.5 | $0.00012 | $0.00089 |
Grade A, and why
agent-hooks 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Lifecycle Hooks
Conventions (not auto-triggers) agents execute at specific lifecycle points. Team Lead includes hook reminders in delegation prompts; specialists follow them in their own workflow.
on-session-start → [work loop] → on-session-end
↓ ↑
on-pre-delegate → on-post-delegate
on-session-start
| # | Action |
|---|---|
| 1 | rg -n "keyword" .opencastle/LESSONS-LEARNED.md |
| 2 | cat .opencastle/SESSION-CHECKPOINT.md (resume if exists) |
| 3 | rg -n "ERROR|FAIL" .opencastle/AGENT-FAILURES.md || true |
| 4 | cat .opencastle/agents/skill-matrix.json | jq '.bindings' — load domain skills |
See HOOKS-REFERENCE.md for extended startup checks (approval polling, skill-matrix verification).
on-session-end
HARD GATE — every session gets a record in
.opencastle/logs/events.ndjson, written before you yield, one per task, never batched retrospectively. Load observability-logging for the Pre-Response Quality Gate.
| # | Action |
|---|---|
| 1 | opencastle doctor |
| 2 | opencastle log --type session ... |
| 3 | Write .opencastle/SESSION-CHECKPOINT.md if work is incomplete |
| 4 | Flag for memory merge if 5+ new lessons |
on-pre-delegate — Team Lead only
| # | Check |
|---|---|
| 1 | Tracker issue exists (gh issue view TAS-XX) |
| 2 | File partition clean (comm -12 <(sort agent1-files) <(sort agent2-files) = empty) |
| 3 | Upstream deps Done (gh issue view TAS-XX --json state -q '.state' = CLOSED) |
| 4 | Prompt has exact file paths + acceptance criteria |
| 5 | Prompt includes "Read LESSONS-LEARNED.md first" |
| 6 | 5+ files → load context-map skill |
All 6 must pass before the sub-agent is dispatched. See HOOKS-REFERENCE.md for example commands per check.
on-post-delegate — Team Lead only
| # | Action |
|---|---|
| 1 | ⛔ opencastle log --type=delegation --issue=TAS-XX --status=complete |
| 2 | Run fast-review skill |
| 3 | Lint, typecheck, and test (commands via the codebase-tool slot) |
| 4 | gh issue view TAS-XX --json body -q '.body' — verify each AC met |
| 5 | If agent retried → verify lesson added via self-improvement |
| 6 | Move to Done or re-delegate; 3rd failure → .opencastle/AGENT-FAILURES.md |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 79 lines · 122 tokens per session scan A ff4a5127b780
agent-hooks is a skill published in the GitHub repository monkilabs/opencastle (61 stars, last pushed 5d ago), licensed MIT. It adds 122 tokens to every session and 886 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 2026-08-30.
Other skills, from other repositories
product-architect
Complete product development system with 64 agents and 35 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan…
codex-delegation
Use when a coding task would benefit from delegating work to Codex in the background — a deep independent second opinion, security or architecture analysis, or a parallel implementation running while the session continues. Lets Claude drive the codex companion itself (task, review, status --wait, result) without the…
cursor-delegation
Use when a coding task would benefit from delegating work to Cursor in the background — fast parallel implementation, scaffolding, or an everyday review running while the session continues. Lets Claude drive the cursor companion itself (task, review, status --wait, result) without the user typing /cursor: commands.
cursor-cli-runtime
Internal helper contract for calling the cursor-companion runtime from Claude Code.
cursor-prompting
Internal guidance for composing cursor-agent prompts and picking models for coding, review, diagnosis, and research tasks inside the Cursor Claude Code plugin.
goal-runner
Use when the user asks to advance, continue, or work on the project's long-horizon goal (or to set one up) — the policy for goal-driven increments driven through the goal companion, one increment at a time, delegated via the codex/cursor delegation skills, honestly recorded.