plan-feature

plan-feature is a skill for Claude Code, Codex from Karthick-Ramachandran/persist-os. It costs 45 tokens per session (489 once invoked), scanned A, original, MIT.

A planning process that turns an approved product requirements document into an implementation plan. It identifies affected architecture and modules, orders the engineering tasks, defines tests, and records how completion will be shown.

In plain words
What is it for?
Use it to create feature plans, task lists, architecture-impact notes, and test plans from requirements, acceptance criteria, project documentation, and known constraints.
Why use it?
It gives an implementation agent a shared scope and clear checks, reducing missed dependencies, unclear ownership, and untested requirements.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to create feature plans, task lists, architecture-impact notes, and test plans from requirements, acceptance criteria, project documentation, and known constraints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karthick-ramachandran/persist-os/plan-feature
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.

Any agent
npx skills add Karthick-Ramachandran/persist-os --skill plan-feature
Clone the repo
git clone --depth 1 https://github.com/Karthick-Ramachandran/persist-os

Made for: Claude Code, Codex.

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.

agentmods badge for plan-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/plan-feature/github.svg)](https://agentmods.dev/skills/karthick-ramachandran/persist-os/plan-feature)
Your own site
<a href="https://agentmods.dev/skills/karthick-ramachandran/persist-os/plan-feature"><img src="https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/plan-feature/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.

agentmods 80×15 button for plan-feature

Your own site · 80×15
<a href="https://agentmods.dev/skills/karthick-ramachandran/persist-os/plan-feature"><img src="https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/plan-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 489 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00489
Opus 5 $0.00023 $0.00244
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00005 $0.00049

Measured 10d ago against content hash 598b0d78c06b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 10d 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.

.agents/skills/plan-feature/SKILL.md · 68 lines

What it actually says

Skill: Plan Feature

Purpose

Turn product intent into a scoped engineering plan that an implementation agent can follow safely.

Inputs

  • Feature PRD.
  • Acceptance criteria.
  • Relevant module or architecture docs.
  • Known constraints or release target.

Required Reading

  • docs/10-architecture/ARCHITECTURE.md
  • docs/10-architecture/FILE_WRITE_POLICY.md
  • docs/20-security/SECURITY_MODEL.md
  • docs/50-quality/QUALITY_GATES.md
  • docs/60-engineering/ENGINEERING_STANDARDS.md
  • Relevant feature docs under docs/40-features/
  • Relevant module docs under docs/30-modules/
  • Relevant ADRs under docs/adrs/

Output Files

  • docs/40-features/<feature>/PLAN.md
  • docs/40-features/<feature>/TASKS.md
  • docs/40-features/<feature>/ARCHITECTURE_IMPACT.md
  • docs/40-features/<feature>/TEST_PLAN.md

Process

  1. Restate the feature objective and acceptance criteria.
  2. Identify modules, docs, templates, and tests affected.
  3. Document architecture impact and ADR needs.
  4. Break work into ordered tasks with clear completion evidence.
  5. Define tests from requirements, risk, security invariants, and regressions.
  6. For module requests, treat the module as a mini product and create feature delivery docs before implementation tasks.

Stop Conditions

Stop and request human decision if:

  • Requirements are missing or contradictory.
  • Architecture impact cannot be determined.
  • The plan conflicts with engineering standards.
  • A task requires changing accepted non-goals.
  • A module request tries to start implementation before PRD, acceptance, architecture impact, test plan, and tasks exist.

Quality Bar

  • Tasks are ordered and independently reviewable.
  • Tests map to acceptance criteria and risks.
  • Architecture impact is explicit.
  • Engineering standards are accounted for in tasks and completion evidence.
  • The plan does not include implementation code when only planning is requested.
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. 10d ago First seen · 68 lines · 45 tokens per session scan A 598b0d78c06b

Subscribe to this mod's changes

plan-feature is a skill published in the GitHub repository Karthick-Ramachandran/persist-os (8 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 489 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 2026-08-31.

Related

Other skills, from other repositories

actual

Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, plus the Actual AI platform surface: login, logout, whoami, and advisor (org-scoped architecture Q&A). Covers all 5 runners (claude-cli…

actual-software/actual-skill · 157 tokens

architecture-governance

Keep code changes conformant to a repo's real, declared architecture using ArchSteer. Use when starting work in an unfamiliar repo, before finishing/committing an architecturally significant change (new dependency, new data access, new external call, new layer), or when asked about a codebase's architecture, layers…

einvoice-dev1/archsteer · 73 tokens

work

Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.

automagik-dev/genie · 26 tokens

openlore-brainstorm

Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.

clay-good/OpenLore · 40 tokens

trace

Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.

automagik-dev/genie · 25 tokens

preview-design

Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…

egregore-labs/egregore · 71 tokens