Agent skill

ratchet

Brownian Ratchet progress gates for RPI workflow. Check, record, verify. Triggers: "check gate", "verify progress", "ratchet status".

Stars 271
Forks 24

Install this agent skill to your Project

npx add-skill https://github.com/boshu2/agentops/tree/main/skills-codex/ratchet

SKILL.md

Ratchet Skill

Track progress through the RPI workflow with permanent gates.

Note: $ratchet tracks and locks progress. It does not “run the loop” by itself—pair it with $crank (epic loop) or $swarm (Ralph loop) to actually execute work.

The Brownian Ratchet

Progress = Chaos × Filter → Ratchet
Phase What Happens
Chaos Multiple attempts (exploration, implementation)
Filter Validation gates (tests, $vibe, review)
Ratchet Lock progress permanently (merged, closed, stored)

Key insight: Progress is permanent. You can't un-ratchet.

Execution Steps

Given $ratchet [command]:

status - Check Current State

bash
ao ratchet status 2>/dev/null

Or check the chain manually:

bash
cat .agents/ao/chain.jsonl 2>/dev/null | tail -10

check [step] - Verify Gate

bash
ao ratchet check <step> 2>/dev/null

Steps: research, plan, implement, vibe, post-mortem

record [step] - Record Completion

bash
ao ratchet record <step> --output "<artifact-path>" 2>/dev/null

Or record manually by writing to chain:

bash
echo '{"step":"<step>","status":"completed","output":"<path>","time":"<ISO-timestamp>"}' >> .agents/ao/chain.jsonl

skip [step] - Skip Intentionally

bash
ao ratchet skip <step> --reason "<why>" 2>/dev/null

Workflow Steps

Step Gate Output
research Research artifact exists .agents/research/*.md
plan Plan artifact exists .agents/plans/*.md
implement Code + tests pass Source files
vibe $vibe passes .agents/vibe/*.md
post-mortem Learnings extracted .agents/learnings/*.md

Chain Storage

Progress stored in .agents/ao/chain.jsonl:

json
{"step":"research","status":"completed","output":".agents/research/auth.md","time":"2026-01-25T10:00:00Z"}
{"step":"plan","status":"completed","output":".agents/plans/auth-plan.md","time":"2026-01-25T11:00:00Z"}
{"step":"implement","status":"in_progress","time":"2026-01-25T12:00:00Z"}

Key Rules

  • Progress is permanent - can't un-ratchet
  • Gates must pass - validate before proceeding
  • Record everything - maintain the chain
  • Skip explicitly - document why if skipping a step

Examples

Check RPI Progress

User says: $ratchet status

What happens:

  1. Agent calls ao ratchet status 2>/dev/null to check current state
  2. CLI reads .agents/ao/chain.jsonl and parses progress
  3. Agent reports which steps are completed, in-progress, or pending
  4. Agent shows output artifact paths for completed steps
  5. Agent identifies next gate to pass

Result: Single-screen view of RPI workflow progress, showing which gates passed and what's next.

Record Step Completion

Skill says: After $research completes

What happens:

  1. Agent calls ao ratchet record research --output ".agents/research/auth.md"
  2. CLI appends completion entry to .agents/ao/chain.jsonl
  3. Agent locks research step as permanently completed
  4. Agent proceeds to plan phase knowing research gate passed

Result: Progress permanently recorded, gate locked, workflow advances without backsliding.

Troubleshooting

Problem Cause Solution
ao ratchet status fails ao CLI not available or chain.jsonl missing Manually check .agents/ao/chain.jsonl or create empty file
Step already completed error Attempting to re-ratchet locked step Use ao ratchet status to check state; skip if already done
chain.jsonl corrupted Malformed JSON entries Manually edit to fix JSON; validate each line with jq -c '.' <file>
Out-of-order steps Implementing before planning Follow RPI order strictly; use --skip only with explicit reason

Local Resources

scripts/

  • scripts/validate.sh

Expand your agent's capabilities with these related and highly-rated skills.

boshu2/agentops

swarm

Spawn isolated Codex sub-agents for parallel task execution using the current runtime primitives. Triggers: "swarm", "spawn agents", "parallel work", "run in parallel", "parallel execution".

271 24
Explore
boshu2/agentops

council

Multi-perspective review for Codex using the current sub-agent runtime. Triggers: "council", "get consensus", "multi-model review", "multi-perspective review", "council validate", "council brainstorm", "council research".

271 24
Explore
boshu2/agentops

openai-docs

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.

271 24
Explore
boshu2/agentops

crank

Hands-free epic execution for Codex using wave-based sub-agents and lead-side validation. Triggers: "crank", "run epic", "execute epic", "run all tasks", "hands-free execution", "crank it".

271 24
Explore
boshu2/agentops

pr-retro

Learn from PR outcomes. Analyzes accept/reject patterns and updates contribution lessons. Triggers: "pr retro", "learn from PR", "PR outcome", "why was PR rejected", "analyze PR feedback".

271 24
Explore
boshu2/agentops

pre-mortem

Validate a plan or spec before implementation using multi-model council. Answer: Is this good enough to implement? Triggers: "pre-mortem", "validate plan", "validate spec", "is this ready".

271 24
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results