Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add oborchers/fractional-cto/plugin install planning-toolsWrote 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/oborchers/fractional-cto/using-planning-tools)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/using-planning-tools"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/using-planning-tools/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.
<a href="https://agentmods.dev/skills/oborchers/fractional-cto/using-planning-tools"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/using-planning-tools.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00244 | $0.04006 |
| Opus 5.5 | $0.00098 | $0.01602 |
| Sonnet 5.5 | $0.00049 | $0.00801 |
| Haiku 4.5 | $0.00024 | $0.00401 |
Grade A, and why
using-planning-tools 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 5d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Why not grep the transcript for `~/.claude/plans/<slug>.md` paths?** That matches any plan path mentioned in conversation (e.g., `ls` output), not just the session's true plan slug. The `"slug"` field is set by Claude Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning Tools
This plugin provides two complementary workflows on top of Claude Code's plan mode:
- Per-session plan-file management — Claude Code stores each session's plan at
~/.claude/plans/<slug>.md. The plugin's/planning-tools:plan-deletecommand cleans these up. - Master-plan authoring — long, multi-phase planning documents that live in the user's project (e.g.,
context/tickets/,docs/plans/) and decompose work into actionable phases. The plugin's/planning-tools:plan-context,/planning-tools:plan-master, and/planning-tools:plan-verifycommands cover this lifecycle.
How to Access Skills
Use the Skill tool to invoke any skill by name. When invoked, follow the skill's guidance directly.
Commands
| Command | Triggers On |
|---|---|
/planning-tools:plan-context [topic] [--domains a,b,c] |
Pre-loading context for a future master plan. Stage 1 Triage decides domains, Stage 2 Announce prints them and continues without asking (override via --domains), Stage 3 dispatches parallel plan-context-worker agents (one per domain), Stage 4 verifies findings with direct Reads. Emits a scope report. NO plan file written. |
/planning-tools:plan-master <topic> [--context <path>] [--domains a,b,c] [--out <path>] |
Drafting a multi-phase master plan. Reuses a prior /planning-tools:plan-context report if --context is supplied; otherwise runs the same Triage + Explore + Verify pre-flight (domains decided autonomously, no prompt). Then dispatches plan-master-architect (opus) to synthesize. Writes to a project-local path without asking: --out wins, else the first existing of context/tickets/, docs/plans/, .claude/plans/master/ (creates context/tickets/ if none). Never overwrites silently (-2 suffix). |
/planning-tools:plan-open-questions [path] [question-number] |
Walking through open questions interactively — from any source, not just a master plan. Resolves the source via a 4-rung ladder: (1) explicit path, (2) whatever is already in this conversation (a plan read earlier, a /plan-context scope report, worker findings, or questions the user typed), (3) branch-matched master plan (only when a git repo exists — skipped silently otherwise), (4) AskUserQuestion fallback (Point me at a file / I'll paste the questions / Cancel). Never hard-fails. Parses four question shapes (v0.3.0 - **Q<N> — …:** bullets, legacy v0.2.x table, scope-report bullets, free-form conversation lists — the last two auto-numbered Q1..QN). Per question the main conversation reads up to ~5 cited anchors and prints a fixed block: ## Q<N> → Why it matters (1–3 short sentences) → Where it matters (concrete anchors, or an honest "Not tied to a specific file yet") → optional one-line If we get this wrong → 2–4 options with one Recommended and Defer always last. Then one AskUserQuestion per question, never batched. Apply is source-aware: a plan-file source gets the 3-option gate (Apply / Show me the diff first / Discard) and moves answered questions from ## Open Questions to ## Resolved Questions; report-file and conversation sources get a printed summary and no write, no gate. Runs entirely in the main conversation — no subagent dispatch. |
/planning-tools:plan-verify [path] |
Auditing a drafted master plan. If no path is supplied, globs candidates and uses binary-confirm (Proceed with most-recent / Cancel) to pick. Dispatches plan-verifier agent against the plan-verification-checklist skill. Emits Critical/Important/Suggestion findings with a PASS/FAIL verdict. On PASS, optionally appends a - **Verified:** YYYY-MM-DD bullet to the plan's context block (a > **Verified:** line on legacy blockquote plans). |
/planning-tools:plan-tick [phase] [path] |
Auto-ticking provenly-achieved phases in a master plan. Default (no args): detects the current branch, resolves the master plan that matches it, runs the audit inline in the main conversation (file existence + branch diff membership + symbol presence), ticks all phases verdicted ACHIEVED. Manual override /planning-tools:plan-tick <phase>: ticks one phase without audit. Both modes are non-interactive — never asks. No subagent dispatched. Works only on plans conforming to planning-tools:master-plan-methodology v0.2.1+. |
/planning-tools:plan-progress [--final] [--destination <type>:<id>] [--style-from <path>] [--ticket <id>] |
Synthesizing a single dense progress entry for the current branch and applying it at the configured destination (markdown file / Linear comment / GitHub issue/PR comment). Reuses plan-tick's branch + plan resolution. SHA-based idempotency: safe to re-run between phases. Three-way detection on the existing entry: new / in-flight update / completed (3-option refresh prompt). First-run destination selection persists to .claude/planning-tools.local.md. --final flips to shipped state with **Shipped <date> via PR #<N>.** + ✅ heading. Composition runs inline in the main conversation — no subagent dispatched. Style spec, sub-markers, and adapter contracts in planning-tools:progress-methodology. |
/planning-tools:plan-delete |
Clearing the current session's plan file at ~/.claude/plans/<slug>.md. Detects the slug via $CLAUDE_CODE_SESSION_ID + transcript grep, deletes the file, recreates empty, re-reads. Bootstraps with EnterPlanMode → no-op plan → ExitPlanMode if the session has never entered plan mode. |
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.
- 5d ago First seen · 121 lines · 244 tokens per session scan A 5b6c7dd0b630
using-planning-tools is a skill published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 244 tokens to every session and 4,006 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.