executing-plans

A structured way to carry out an existing written implementation plan in batches, with review and verification checkpoints. It treats the plan as the main source of instructions and pauses for feedback after each batch.

In plain words
What is it for?
Loading a plan from project documentation, implementing its tasks in groups, reporting what changed and how it was tested, and continuing after review.
Why use it?
It helps prevent large planned changes from being applied all at once without review and makes missing files, unclear instructions, or failed checks visible early.

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/carbeneai/forge/executingplans
Any agent
npx skills add CarbeneAI/Forge --skill executingplans
Clone the repo
git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00075 $0.03438
Opus 5 $0.00037 $0.01719
Sonnet 5 $0.00015 $0.00688
Haiku 4.5 $0.00007 $0.00344

Measured 2d ago against content hash 5e61645a12a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

executing-plans scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

$ curl -X POST http://localhost:3000/api/login \
.claude/skills/ExecutingPlans/SKILL.md · 670 lines

How it starts

The opening of the file, as written. The whole thing — 670 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Executing Plans

Systematically execute written implementation plans with batch processing, verification checkpoints, and progress reporting.

🎯 Load Full CORE Context

read ${PAI_DIR}/skills/CORE/SKILL.md

When to Activate This Skill

  • "execute the plan at docs/plans/..." → Systematic implementation
  • "implement from the plan" → Follow written specification
  • "start working on the plan" → Batch execution with checkpoints
  • User has written plan ready to execute

Core Philosophy

Plans Are Single Source of Truth

The plan document specifies:

  • What to build
  • How to build it
  • What order to build it
  • How to verify each step

Follow the plan exactly. Don't improvise or "improve" unless explicitly discussed with user.

Batch Execution with Checkpoints

Execute 3 tasks (default), then STOP and report:

  • What was implemented
  • Verification output
  • Current status

Wait for user feedback before continuing. This enables:

  • Course correction if something's wrong
  • User awareness of progress
  • Clear stopping points
  • Better debugging

STOP When Blocked

If you encounter ANY uncertainty:

  • Missing file referenced in plan
  • Unclear instruction
  • Dependency issue
  • Environment problem

STOP and ASK. Never guess or make assumptions.

The Five-Step Process

Step 1: Load and Review Plan

Before starting any work:

  1. Read the entire plan from docs/plans/
  2. Review critically - does it make sense?
  3. Check prerequisites - are they met?
  4. Understand execution order - why this sequence?
  5. Raise concerns before starting

Critical Questions:

  • Is the plan clear and executable?
  • Are prerequisites met?
  • Do file paths exist or need creation?
  • Are dependencies installed?
  • Is codebase state ready for this plan?

If you find issues with the plan, STOP and report them before starting.

Example Review:

## Plan Review

**Plan:** docs/plans/2026-02-03-user-auth.md

**Checked:**
- [x] Prerequisites met (Express running, Vitest configured, bcrypt installed)
- [x] File paths make sense (src/models/, tests/, src/services/)
- [x] Task sequence logical (test-first, then implement)
- [x] Verification steps clear

**Concerns:**
- None - plan looks executable

**Ready to start:** YES

Proceeding with first batch (Tasks 1-3).

Read the full file on GitHub · 670 lines

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 · 670 lines · 75 tokens per session scan A 5e61645a12a0

Subscribe to this mod's changes

executing-plans is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 3,438 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

pentesting-everything

Guides authorized penetration testing with PentestingEverything as the source-grounded knowledge base. Use when scoping an engagement, building domain checklists, hunting a vulnerability class, choosing tools/commands, or drafting evidence-based findings from this repository's Markdown.

m14r41/PentestingEverything · 56 tokens

implementing-devsecops-security-scanning

Integrates Static Application Security Testing (SAST), Dynamic Application Security Testing (DAST), and Software Composition Analysis (SCA) into CI/CD pipelines using open-source tools. Covers Semgrep for SAST, Trivy for SCA and container scanning, OWASP ZAP for DAST, and Gitleaks for secrets detection. Activates for…

xalgorix/xalgorix · 109 tokens

hunt-ato

Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session…

Zyrexnn/Cybermes · 241 tokens

aod-orchestrate

Multi-feature orchestration skill that bridges /aod.blueprint output to parallel wave execution. Groups synced GitHub Issues by ICE priority tier (P0/P1/P2) into sequential waves, creates Task records, spawns batch sessions via the orchestrator API, monitors completion, and reports results. Supports --issues…

davidmatousek/tachi · 110 tokens

security

Claude-powered SAST and SCA security scan skill. Invoked automatically as the Security Scan step (Step 7) of /aod.build (after Design Quality Gate, before Code Simplification) or standalone via /security. Analyzes all code files and dependency manifests changed on the feature branch relative to main for OWASP Top 10…

davidmatousek/tachi · 165 tokens

aod-foundation

Guided post-init workshop that helps new AOD Kit adopters establish product vision and design identity. Two-part flow: Part 1 (Vision) asks 5 guided questions to populate product-vision.md; Part 2 (Design) browses archetypes to generate brand files (brand.md, tokens.css, anti-patterns.md). Supports --vision and…

davidmatousek/tachi · 98 tokens