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 skills add goiltpatpat/patpat --skill patpat-loopgit clone --depth 1 https://github.com/goiltpatpat/patpatWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/goiltpatpat/patpat/patpat-loop)<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-loop"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-loop.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00048 | $0.02095 |
| Opus 5 | $0.00024 | $0.01047 |
| Sonnet 5 | $0.00010 | $0.00419 |
| Haiku 4.5 | $0.00005 | $0.00210 |
Grade A, and why
patpat-loop 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patpat Loop
/patpat and /patpat-loop are the same entry point. Codex uses $patpat or $patpat-loop.
Patpat is one system. The operating protocol is the spine: judgment, safety, git, and evidence. Playbooks and principles specialize the work without overriding that spine.
This mode stays on across later turns after explicit invocation. Trusted host hooks may persist it across resume and compaction. Without a host-observed receipt, apply it only for the current session and report current-turn-only after a restart. Say disable /patpat to opt out. Do not infer activation from a task that merely resembles a playbook.
Start
Classify the task first from signals: reversibility, uncertainty, blast radius, auth, security, billing, secrets, architecture, cross-cutting, duration, delivery intent, and parallelism need. First activation is context, not a risk signal. First activation alone must not force a full protocol read.
Scale start from that classification:
- Clear, bounded, reversible, and local (including on first activation): lightweight start. Begin with the cheapest useful observation. Read only the matched playbook and the principles it links. Do not open a mandatory todo list. Do not require a numbered checklist. Mutating work still defines the 5-field proof contract before editing and still verifies on the authoritative surface.
- Ambiguous, structural, high-risk, delivery-intent, or multi-step sequencing uncertainty: fuller start. Read the operating protocol in full when needed, skim the principle index, and keep a compact checklist with a verify check per step when sequencing earns it. A skipped step stays listed with
skip: <reason>. - Durable, dependent, or resumable multi-phase work: use
patpat-runformal state machinery.
Inspect, execute, or measure before asking. Ask only for product preference, authority, a destructive action, security, or another human-only choice. Do not expose named user-selectable modes.
What ships with it
49 files 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.
- agents/openai.yaml 244 B
- playbooks/architecture-change.md 1.5 KB
- playbooks/arena.md 2.5 KB
- playbooks/authorized-delivery.md 1.2 KB
- playbooks/automation-design.md 1.0 KB
- playbooks/autopilot.md 2.9 KB
- playbooks/behavior-preserving-refactor.md 766 B
- playbooks/behavioral-eval.md 1.9 KB
- playbooks/bespoke-workflow.md 1010 B
- playbooks/blast-radius.md 1.0 KB
- playbooks/bounded-change.md 886 B
- playbooks/default-delivery.md 2.7 KB
- playbooks/defect.md 1.6 KB
- playbooks/independent-review.md 3.3 KB
- playbooks/investigation.md 2.9 KB
- playbooks/issue-loop.md 2.8 KB
- playbooks/learning.md 1.4 KB
- playbooks/metric-hillclimb.md 1.3 KB
- playbooks/multi-phase-run.md 1.5 KB
- playbooks/pause-safely.md 1.9 KB
- playbooks/performance.md 845 B
- playbooks/pr-babysit.md 4.1 KB
- playbooks/pr-drive.md 1.2 KB
- playbooks/project-verifier.md 2.2 KB
- playbooks/prototype.md 756 B
- playbooks/rationale-forensics.md 1.8 KB
- playbooks/regression-first.md 1.4 KB
- playbooks/runtime-forensics.md 783 B
- playbooks/session-takeover.md 1.9 KB
- playbooks/skill-change.md 1003 B
- playbooks/swarm.md 1.6 KB
- playbooks/trace-forensics.md 729 B
- playbooks/visual-equivalence.md 1.1 KB
- playbooks/worktree-cleanup.md 1.5 KB
- principles/boundary-discipline.md 384 B
- principles/earned-parallelism.md 1.5 KB
- principles/encode-lessons.md 480 B
- principles/fix-root-causes.md 429 B
- principles/idempotent-effects.md 428 B
- principles/preserve-safety.md 733 B
- principles/proof-over-proxy.md 2.0 KB
- principles/repository-truth.md 701 B
- principles/sequence-verifiable-units.md 582 B
- principles/shape-before-logic.md 745 B
- principles/smallest-safe-change.md 1017 B
- references/earned-representation.md 1.3 KB
- references/execution-graph.md 3.3 KB
- references/operating-protocol.md 8.7 KB
- references/route-catalog.md 4.3 KB
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 Changed · -3 lines 450e430c15eb
- 3d ago Changed · +1 lines 8ad96434af43
- 7d ago First seen · 115 lines · 48 tokens per session scan A 8eec7757e889
patpat-loop is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 2,095 once invoked, about $0.0002 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 skills, from other repositories
Repository Knowledge Management
Create and maintain the Repository Knowledge Base using the official Agentic Engineering playbooks.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…