update-plan

update-plan is a skill for Claude Code from markmhendrickson/ateles. It costs 25 tokens per session (964 once invoked), scanned A, original, MIT.

A session-ending planning tool that updates a Neotoma plan—a stored record of project goals, decisions, and next steps—to match current work.

In plain words
What is it for?
It helps revise project todos, decisions, next steps, and plan notes after a work session.
Why use it?
It prevents plans from becoming inaccurate when tasks are completed, changed, or blocked.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit It helps revise project todos, decisions, next steps, and plan notes after a work session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/markmhendrickson/ateles/update-plan
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 markmhendrickson/ateles --skill update-plan
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code.

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 update-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/update-plan.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/update-plan)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/update-plan"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/update-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 964 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00025 $0.00964
Opus 5 $0.00013 $0.00482
Sonnet 5 $0.00005 $0.00193
Haiku 4.5 $0.00003 $0.00096

Measured 4d ago against content hash 4175c65669d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

update-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 4d 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.

.claude/skills/update-plan/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

update-plan

Update a Neotoma plan entity to accurately reflect what was built and decided this session.

Always run this at the end of any session that makes progress against a plan. Also invoke mid-session if a significant decision is settled that should not be lost to context exhaustion.

Inputs

  • plan_entity_id: the Neotoma entity ID of the plan matching this session's workstream. There is no global default — resolve it by retrieve_entities(entity_type=plan, search=<workstream>) and pick the closest match, or create a new plan if none fits. Only use ent_99ace4dd6673aa36ed08b1fe ("Ateles Agent Swarm Architecture") when the session's work is swarm-architecture itself; never funnel unrelated workstreams (tax, release engineering, website, cloud hosting) into it.
  • Session context: what was built, what was decided, what is now blocked or unblocked

Steps

Step 1: Retrieve current plan snapshot

mcp__mcpsrv_neotoma__retrieve_entity_snapshot(entity_id=<plan_entity_id>, format="markdown")

Step 2: Diff todos against reality

For each item in the todos array:

  • Mark "status": "done" if completed this session or in prior sessions
  • Mark "status": "in_progress" if actively being worked
  • Leave "status": "pending" if not yet started
  • Add a "notes" field on any item where implementation details matter (entity IDs, file paths, caveats, PR numbers)
  • Add new todos for work identified this session that isn't already listed

Step 3: Update decisions map

Add or correct entries for any decisions settled this session. Each entry is a key (snake_case decision name) → single-sentence value capturing the what and why. correct replaces the entire decisions map, so RE-READ the current map from Step 1, then write back the full map with only your keys added/updated and every pre-existing key preserved. Never delete existing entries, and never rebuild the map from a stale in-memory copy — that silently drops other sessions' decisions. The same re-read-and-merge rule applies to the todos array.

Read the full file on GitHub · 89 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. 4d ago First seen · 89 lines · 25 tokens per session scan A 4175c65669d7

Subscribe to this mod's changes

update-plan is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 964 once invoked, about $0.0001 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 2026-09-03.