planr-loop

An autonomous Planr workflow for driving one feature or scope from a plan through implementation and trusted verification. Planr is a local-first tool that coordinates coding tasks, evidence, approvals, and reviews.

In plain words
What is it for?
Use it to execute a feature, make and verify changes, consume compatible tasks, handle recovery, and reach audit-backed completion.
Why use it?
It keeps related work moving under one plan and stops only when the defined completion conditions, required evidence, and material reviews are satisfied.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/instructa/planr/planr-loop
Any agent
npx skills add instructa/planr --skill planr-loop
Clone the repo
git clone --depth 1 https://github.com/instructa/planr

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,424 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.01424
Opus 5 $0.00017 $0.00712
Sonnet 5 $0.00007 $0.00285
Haiku 4.5 $0.00003 $0.00142

Measured 2d ago against content hash 1f8359ee2b10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planr-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 2d 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.

plugins/planr/skills/planr-loop/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planr Loop

This skill is the complete sequential execution contract. Do not reload $planr or $planr-work after the request has routed here.

The invoking session is the default maker. It inspects and changes product source directly, keeps one stable worker identity, and consumes compatible typed packets until a genuine stop. Do not spawn a coordinator or maker for the default path.

Evaluation subcommands run only when the user requests them, an acceptance criterion requires them, or the maintainer release workflow invokes them. Never run an eval as routine loop work.

Evidence admission guard

Read and apply the canonical Evidence ownership guard before loop execution. Do not duplicate or reinterpret it here.

Execute the loop

Use one plan and a checkable stop condition. The default iteration budget is 10. Refuse a request that combines unrelated goals.

  1. Recover the stored GOAL CONTRACT <plan-id>. If it is absent, store one that requires settled outcomes, binding Evidence, clear approvals, and only the material ReviewGates required by policy or the plan. Run planr stop activate --plan <plan-id> once for the host thread. Codex hosts let Planr use CODEX_THREAD_ID; other hosts provide one stable explicit session.

  2. Run planr plan audit <plan-id> --json. Exit when holds: true. If scope, the checked build plan, or the map is missing, use $planr-plan or $planr-task-graph in this session, then return to the audit.

  3. Become the maker in this session. Export one stable identity, then lease only plan-scoped outcome work:

    export PLANR_WORKER_ID="maker-<stable-session-id>"
    planr pick --work-type code --plan <plan-id> --json
    

    Require work_packet.execution_state.schema_version to equal planr.execution_state.v2. Treat its budget as opaque authority. Branch only on work_packet.kind and optional work_packet.mode.

    • kind: "outcome" is maker work. Read the linked plan, inspect product source, implement the smallest correct slice, run the repository-selected checks once, and settle with planr done <item-id> ... --next --json.
    • mode: "finding_repair" repairs only the named findings on the same ReviewGate. It creates no fix item. Resolve the findings and stop for re-review.
    • kind: "hold" stops. Never replace policy with host behavior.

Read the full file on GitHub · 123 lines

Files

What ships with it

4 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.

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.

  1. 2d ago First seen · 123 lines · 34 tokens per session scan A 1f8359ee2b10

Subscribe to this mod's changes

planr-loop is a skill published in the GitHub repository instructa/planr (71 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 1,424 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 2026-08-30.

Related

Other skills, from other repositories

auth-web-cloudbase

CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.

TencentCloudBase/CloudBase-AI-Toolkit · 38 tokens

fix-codesign-error

Slash command that inspects a macOS signing or entitlement failure and explains the minimum fix path. Invoke explicitly with /fix-codesign-error — this skill never self-triggers.

robinebers/openusage · 42 tokens

browse-and-evaluate

Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.

MoizIbnYousaf/Ai-Agent-Skills · 43 tokens

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

griddynamics/rosetta · 27 tokens

loop-engineering

Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).

huytieu/COG-second-brain · 63 tokens

telnyx-messaging-hosted-curl

Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.

team-telnyx/ai · 45 tokens