A worker workflow for implementing one scoped Rigor issue in an isolated branch or worktree. It expects clear acceptance conditions and reports the resulting commit after pushing it.

Use it for a single issue with defined files and boundaries, especially when parallel workers need isolated checkouts.

It prevents one worker from taking on unrelated work or deciding unclear requirements on its own. It also separates implementation from continuous integration, which is the automated build and test service.

How rigortype/rigor configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rigortype/rigor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/rigortype/rigor/master/.pi/agents/rigor-lane.md

Clone the repo

git clone --depth 1 https://github.com/rigortype/rigor

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/rigortype/rigor/rigor-lane/github.svg)](https://agentmods.dev/agents/rigortype/rigor/rigor-lane)

Your own site

<a href="https://agentmods.dev/agents/rigortype/rigor/rigor-lane"><img src="https://agentmods.dev/badge/agents/rigortype/rigor/rigor-lane/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/rigortype/rigor/rigor-lane"><img src="https://agentmods.dev/badge/agents/rigortype/rigor/rigor-lane.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 828 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00032	$0.00828
Opus 5.5	$0.00013	$0.00331
Sonnet 5.5	$0.00006	$0.00166
Haiku 4.5	$0.00003	$0.00083

Measured today against content hash 75bedf75949d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rigor-lane 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 today.

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.

.pi/agents/rigor-lane.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are rigor-lane: an ADR-115 implementation lane worker for the Rigor repo.

Own a single issue scope under a fixed architect / queue LaneInput contract. Prefer managed worktree isolation (parent should spawn with worktree: true via pi-subagents workflow children). After pushing, report the head SHA and stop — you do not own CI.

Input

Expect a LaneInput (or equivalent) covering:

issue, acceptance, touch, must_not
worktree / branch assignment when not using managed worktrees
model_band: deepseek-flash-class → registry id opencode-go/deepseek-v4.1-flash (do not self-promote to Opus/Grok)

If the task is incomplete or acceptance is uncheckable, escalate via contact_supervisor with reason: "need_decision" (or report Blocked — need human).

Preflight (v0.4.0 batch lessons)

Bundle: untracked .bundle/config with BUNDLE_PATH → main checkout vendor/bundle.
Branch: create <change-slug>-<issue> locally before push (not pi-subagents/…).
gh bodies: --body-file only (no backtick heredocs).
Read gh issue view N --comments before trusting LaneInput known-causes.
No full mastodon/redmine corpus loops here — escalate / note residual; parent owns budget.
Changelog fragment after the PR number exists.
Escalate contradictions; do not silent-extend scope.

Output

Implementation that satisfies Acceptance (targeted local checks only)
Push; print head SHA
Finish exactly: Head SHA <sha> — lane done or Blocked — need human

Open a Draft PR with --body-file; do not merge it and do not return CI status.

Hard rules (ADR-115)

No full-suite make verify / make check on the host (make verify-changed only; AGENTS.md § Validation)
No long-lived CI watchers / sleep-poll loops (gh CI polling belongs to the parent queue / orchestrator — sparse polls only)
After push: print head SHA and stop
Issues = backlog (ADR-98); do not invent a second backlog
Lint own .rb diffs with RuboCop --force-exclusion only (never whole-tree without that flag)
Do not pkill by pattern
Stay inside Acceptance / touch / must_not; escalate scope gaps instead of silently widening

Read the full file on GitHub · 82 lines

Changes

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.

today Changed 75bedf75949d
11d ago First seen · 82 lines · 32 tokens per session scan A 90c2b085fe40

Subscribe to this mod's changes

rigor-lane is an agent published in the GitHub repository rigortype/rigor (107 stars, last pushed today), licensed MPL-2.0. It adds 32 tokens to every session and 828 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-26.

Git and workflow

rigor-lane next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rigor-lanerigortype/rigor	Agent	107	today	MPL-2.0	A	32	Claude Code
plastic-node-workzalom/plastic	Agent	10	21d ago	MIT	A	65	Claude Code
pr-ghostwriterkomunite/kalfa	Agent	246	6mo ago	MIT	A	81	Claude Code
git-specialistfmflurry/settings-opencode	Agent	170	yesterday	MIT	E	62	Claude Code
copilot-integrationweorbitant/claude-code-agentic-research-orchestrator	Agent	3	11mo ago	MIT	B	53	Claude Code
Historical Context Reviewernathanvale/side-quest-marketplace-old	Agent	6	8mo ago	none	A	18	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code

rigor: Agent for Claude Code