A workflow for marking a Markdown coding plan as ready for implementation. It adds a UTC timestamp and optional work-ticket ID to the plan file and title.

Use it to freeze a named plan in the ai-plans folder, check whether it is already frozen, and record the freeze time.

It prevents a plan from being changed casually after implementation begins and makes the approved version identifiable.

freeze-plan — Skill for Claude Code by feO2x/guided-coding

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 feO2x/guided-coding --skill freeze-plan

Clone the repo

git clone --depth 1 https://github.com/feO2x/guided-coding

Made for: Claude Code.

Or install guided-coding, the plugin that ships this one along with the rest of its 8 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/feo2x/guided-coding/freeze-plan/github.svg)](https://agentmods.dev/skills/feo2x/guided-coding/freeze-plan)

Your own site

<a href="https://agentmods.dev/skills/feo2x/guided-coding/freeze-plan"><img src="https://agentmods.dev/badge/skills/feo2x/guided-coding/freeze-plan/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/feo2x/guided-coding/freeze-plan"><img src="https://agentmods.dev/badge/skills/feo2x/guided-coding/freeze-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 519 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.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.00519
Opus 5.5	$0.00007	$0.00208
Sonnet 5.5	$0.00004	$0.00104
Haiku 4.5	$0.00002	$0.00052

Measured 1mo ago against content hash dbd9208521de, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

freeze-plan 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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

guided-coding-freeze-plan — 88% identical, 7 lines differ

claude-plugin/claude-skills/freeze-plan/SKILL.md · 39 lines

What it actually says

Freeze a Plan

Freezing a plan means providing a timestamp, both at the beginning of its file name and directly after its title. An optional <ticket-id> is also inserted into the file name after the timestamp.

The plan is then considered ready for implementation, only its acceptance criteria are allowed to be checked off by the implementer.

The target plan should be already mentioned in the conversation, typically in the format <short-title>.md. If not, first inspect the ai-plans/ folder for a single plan Markdown file which is untracked or has changes. Otherwise, ask the user to provide the path to the plan file.

If the plan already carries a timestamp in its file name or a *Frozen at ...* line below its title, it is frozen. Report this to the user and stop.

1. Determine the Timestamp

The <timestamp> is UTC in the format YYYY-MM-DD-HHMM. Use these commands to get it:

date -u +%F-%H%M on Unix-based shells
(Get-Date).ToUniversalTime().ToString("yyyy-MM-dd-HHmm") on PowerShell

2. Determine an Optional Ticket ID

Plans are typically associated with a <ticket-id>. This is the ID of a work item such as a GitHub issue or a Jira task. If you don't know it from the conversation yet, ask the user to provide it. Note that not each plan needs to be associated with a <ticket-id>.

3. Change the Plan File Name

<timestamp>-<ticket-id>-<short-title>.md if <ticket-id> is present
<timestamp>-<short-title>.md otherwise

If a file with this name already exists in ai-plans/, report the collision and stop. Never overwrite an existing file.

4. Stamp the Plan Content

Right beneath the # Title, insert the following line: *Frozen at <timestamp-utc>*, where <timestamp-utc> is an ISO 8601 timestamp of the existing <timestamp> used for the file, precise to the minute. E.g., the <timestamp> 2026-09-17-0231 for the file name becomes 2026-09-17T02:31Z.

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.

1mo ago First seen · 39 lines · 18 tokens per session scan A dbd9208521de

Subscribe to this mod's changes

freeze-plan is a skill published in the GitHub repository feO2x/guided-coding (6 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 519 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-18.

Planning Project management agent-skills

story-readiness

Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.

Donchitos/Claude-Code-Game-Studios · 48 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

qa-project-bootstrap

Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…

petrkindlmann/qa-skills · 124 tokens

remove

Remove a deployed framework or addon from the current workspace.

jmagly/aiwg · 12 tokens