Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Plan

ASecurity

Turn a supplied specification or desired outcome into one ledger-native work item, or an epic with reviewable child slices, without writing spec files into a repository. Use when the operator asks to plan work with Forged or invokes /forged:plan.

2 stars
0 votes
0 copies
0 views
Added 9/3/2026
developmentgobash

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tcashel/forge --skill plan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Plan?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Plan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tcashel-plan/badge)](https://www.skillsdirectory.com/skills/tcashel-plan)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: plan
description: "Turn a supplied specification or desired outcome into one ledger-native work item, or an epic with reviewable child slices, without writing spec files into a repository. Use when the operator asks to plan work with Forged or invokes /forged:plan."
---

# /forged:plan

Position: `forged explain --id "$WORK_ID"` reports lifecycle stage `drafted` after the record exists.
Next: `forged next --repo "$TARGET_REPO"` points each complete record to critique.

Boundary: the lead researches, makes product and architecture judgments, and
authors the operator ledger. Planning never starts provider execution or writes
a specification, hook, setting, or work store into the target repository.

## Author the native record

The ledger record is the execution contract. Preserve supplied requirements
and decisions; inspect only what is needed to verify them and fill gaps. For an
outcome-only request, resolve routine engineering choices within delegated
scope. Both inputs produce the same concise fields, with detail proportional
to the work. Resolve one canonical absolute `metadata.repository`:

| Field | Contract |
| --- | --- |
| `title` | lowercase conventional-commit PR title, at most 70 characters |
| `description` | context and concrete behavior |
| `design` | seam constraints and non-goals |
| `acceptanceCriteria` | observable outcomes and exact gates |
| `notes` | agent instructions, decisions, and unresolved `- [ ]` questions |

Use `schema.md` and `checklist.md` to check the contract; read `research.md`
when discovery is needed and `epic.md` only when considering an epic. Inspect
the relevant repository evidence read-only. Prefer one reviewable task; use an
epic only when real dependencies or independent waves require it. Fully specify
the first wave and make later work honest blocked stubs. The lead resolves
routine engineering choices and asks the operator only about product scope or
external authority.

Prepare the four Markdown bodies outside the repository. Reject a draft that
is missing, unreadable, non-UTF-8, or empty. Each file flag conflicts with its corresponding inline flag.

```bash
WORK_ID="ore-<short-stable-id>"
forged work create --id "$WORK_ID" --title "$TITLE" --kind task --status open \
  --repository "$TARGET_REPO" --description-file "$DESCRIPTION_PATH" \
  --design-file "$DESIGN_PATH" --acceptance-file "$ACCEPTANCE_PATH" \
  --notes-file "$NOTES_PATH"
```

Use `--kind epic` on the plan map and `--status blocked` on any item with an
unresolved question or later-wave assumption. A new task is linked to its epic
and to only genuine prerequisites:

```bash
forged work link --from "$CHILD_ID" --to "$EPIC_ID" --kind parent-child
forged work link --from "$CHILD_ID" --to "$BLOCKER_ID" --kind blocks
```

Revise an existing open record under its observed revision. Omitted fields keep
their bytes, but planning passes every reviewed field so the contract is clear:

```bash
forged work update --id "$WORK_ID" --expected-revision "$OBSERVED_REVISION" \
  --title "$TITLE" --description-file "$DESCRIPTION_PATH" \
  --design-file "$DESIGN_PATH" --acceptance-file "$ACCEPTANCE_PATH" \
  --notes-file "$NOTES_PATH"
```

`work promote` preserves the existing title. To change it, first use the
revision-fenced `work update` above, then read the resulting revision before
promoting the completed blocked stub atomically with the four body files:

```bash
forged work promote --id "$WORK_ID" --expected-revision "$OBSERVED_REVISION" \
  --description-file "$DESCRIPTION_PATH" --design-file "$DESIGN_PATH" \
  --acceptance-file "$ACCEPTANCE_PATH" \
  --notes-file "$NOTES_PATH"
```

Stop on a moved revision, reconcile the newer content, then make one fresh
guarded write. Model only actual `blocks` edges; independent siblings stay
independent.

## Readback

Read the authored record and the next action:

```bash
forged work show --id "$WORK_ID"
forged next --repo "$TARGET_REPO"
```

Verify repository identity, fields, questions, status, and edges from the
readback. Use `forged work ready --repo "$TARGET_REPO" --all --full` only when planning
depends on the complete frontier. Report the work id and any exact blocker;
group by wave only for an epic.

## Never

- Do not hide uncertainty in prose or delegate product judgment to a builder.
- Do not create ceremony-only slices or a parallel specification artifact.
- Do not infer readiness from status alone or widen beyond the named repository.
- Do not execute, install software, edit repository policy, or add a tracker.

Attribution

tcasheltcashel
View sourceMore from tcashel →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

281612 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2132 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →