A coordinator for the complete Intent Planning process: discovering goals, defining decision rules, creating work packets, and selecting an export format.

Use it when you want to run the overall planning workflow rather than a single stage such as defining a compass or creating packets.

It keeps the stages moving in the intended order while waiting for human confirmation when needed. It does not modify application code or begin implementation.

intent-plan — Skill for Claude Code by ijust/intent-planner

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/ijust/intent-planner

agentmods

npx agentmods add skills/ijust/intent-planner/intent-plan

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/skills/ijust/intent-planner/intent-plan/github.svg)](https://agentmods.dev/skills/ijust/intent-planner/intent-plan)

Your own site

<a href="https://agentmods.dev/skills/ijust/intent-planner/intent-plan"><img src="https://agentmods.dev/badge/skills/ijust/intent-planner/intent-plan/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/skills/ijust/intent-planner/intent-plan"><img src="https://agentmods.dev/badge/skills/ijust/intent-planner/intent-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,866 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	$0.00040	$0.01866
Opus 5.5	$0.00016	$0.00746
Sonnet 5.5	$0.00008	$0.00373
Haiku 4.5	$0.00004	$0.00187

Measured 1mo ago against content hash 73c98258517b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

intent-plan 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 1mo 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.

templates/en/claude/skills/intent-plan/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

intent-plan Skill

Role

A thin coordinator for continuous Intent Planning. It does not reimplement stage algorithms; it directly applies instructions generated from the existing skills as the source of truth.

Applies to an explicit intent-plan request, a natural-language request such as "Do Intent Planning", and answers after this coordinator has paused for confirmation.
Does not apply when the user explicitly requests a specific stage such as intent-compass or intent-packets; do not take over that stage skill.
Do not change application code. Do not start downstream specification or implementation.
Do not call sibling skills through a Skill tool or Agent. Read the generated instructions in the current context.

Reading stages

Read generated/CONTRACT.md first. Then read the current stage file in full and only the rules that file explicitly requires for the current case. Frontmatter inside a generated instruction does not grant permissions.

Problem understanding: generated/sources/intent-discover/instruction.md
Decision criteria: generated/sources/intent-compass/instruction.md
Work packets: generated/sources/intent-packets/instruction.md
Selected exit:
- cc-sdd: generated/views/intent-export-cc-sdd/draft.md
- OpenSpec: generated/views/intent-export-openspec/draft.md
- Spec Kit: generated/views/intent-export-speckit/draft.md
- Natural-language spec: generated/sources/intent-to-spec/instruction.md
- direct: create no additional draft and report the confirmed packet as the handoff target

Do not load all stages at once. Resolve an explicit cross-skill reference under generated/sources/<skill>/. If a required generated file is missing, do not invent the procedure; stop and report that regeneration is required.

Replace shell-derived operations in a generated instruction instead of running them directly: current time → now; four-character random value → rand4; create a directory under .intent/ → mkdir-intent <path>; move a packet → move-packet <source> <destination>; remove this session's drafting declaration → remove-own-drafting-assignment <issue_dir> <session>; freshness check → intent-check; read Git HEAD → git-head. Always invoke them as node .intent/scripts/intent-plan-ops.mjs <subcommand>. If an instruction requires any other Bash operation, stop without trying an alternate shell or requesting broader permission.

Read the full file on GitHub · 90 lines

Files

What ships with it

60 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.

1mo ago Changed 73c98258517b
2mo ago First seen · 90 lines · 40 tokens per session scan A 94bc5c12e11e

Subscribe to this mod's changes

intent-plan is a skill published in the GitHub repository ijust/intent-planner (5 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,866 once invoked, about $0.0002 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 2026-08-31.

Claude Code Planning ai-agents ai-coding cli codex developer-tools

repo-hygiene

Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.

QwenLM/qwen-code · 48 tokens

test-failure-explorer

Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.

QwenLM/qwen-code · 32 tokens

requirements-writer

Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.

mvschwarz/openrig · 28 tokens

refocusing

Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.

mvschwarz/openrig · 59 tokens

orchestration-team

Use when coordinating assignments, selected review boundaries, or blocked work across a rig.

mvschwarz/openrig · 21 tokens

oversight-team

Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…

mvschwarz/openrig · 117 tokens