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.
git clone --depth 1 https://github.com/andrewvaughan/agent-councilnpx agentmods add skills/andrewvaughan/agent-council/plan-featureWrote 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/andrewvaughan/agent-council/plan-feature)<a href="https://agentmods.dev/skills/andrewvaughan/agent-council/plan-feature"><img src="https://agentmods.dev/badge/skills/andrewvaughan/agent-council/plan-feature.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 | $0.00047 | $0.09505 |
| Opus 5 | $0.00023 | $0.04752 |
| Sonnet 5 | $0.00009 | $0.01901 |
| Haiku 4.5 | $0.00005 | $0.00950 |
Grade A, and why
plan-feature 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 742 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Planning Workflow
Take a feature idea from concept to an approved implementation plan with lean scope, council consensus, and a documented decision record. This skill challenges assumptions, asks hard questions, and pushes back at every stage — before councils review, after councils vote, and before final approval. The goal is to arrive at the strongest possible plan, not to rubber-stamp the first idea.
[!CAUTION] Scope boundary: This skill produces a plan, a decision record, GitHub issue(s), and integrates them into the Product Roadmap project with correct phase assignments. It does NOT write application code, create components, modify database schemas, run tests, create branches for implementation, or perform any build work. If the user asks to start building after the plan is approved, direct them to run
/build-feature <issue-number>— do not begin implementation yourself.
Step 1: Gather Feature Context
Ask the user to describe:
- What the feature does (user-facing behavior)
- Who it is for (target users)
- Why it matters (business or product value)
- Constraints (time, technical, budget, dependencies)
If the user provides a GitHub issue number, fetch the issue details:
gh issue view <number> --json title,body,labels,state,number
Track the source issue number — if planning was initiated from a GitHub issue, store the issue number for later updates in Steps 3, 5, and 7.
Already-Planned Check
If the issue has the build-ready label, it has already been through /plan-feature and was deemed sufficiently planned. Warn the user before proceeding:
[!WARNING] Issue #<number> already has the
build-readylabel, which means/plan-featurehas been run on it before. Re-running will create a new decision record and may create duplicate implementation issues.
Ask the user whether to:
- (a) Continue anyway (re-plan from scratch, e.g., if requirements changed significantly)
- (b) Stop and use the existing plan (run
/build-feature <number>instead)
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.
- 8d ago First seen · 742 lines · 47 tokens per session scan A f76876374c39
plan-feature is a skill published in the GitHub repository andrewvaughan/agent-council (13 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 9,505 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.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.