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.
npx skills add markmhendrickson/ateles --skill update-plangit clone --depth 1 https://github.com/markmhendrickson/atelesWrote 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/markmhendrickson/ateles/update-plan)<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>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00964 |
| Opus 5 | $0.00013 | $0.00482 |
| Sonnet 5 | $0.00005 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00096 |
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.
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 byretrieve_entities(entity_type=plan, search=<workstream>)and pick the closest match, or create a new plan if none fits. Only useent_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.
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.
- 4d ago First seen · 89 lines · 25 tokens per session scan A 4175c65669d7
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.
Other skills, from other repositories
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.
continue
Autonomous work — find and execute ready tasks.
prd
A Product Requirements Document (PRD) writer for large software initiatives. A PRD records the problem, goals, requirements, assumptions, and evidence before implementation begins.
roadmap
An implementation plan made from a technical specification, organized into phases, milestones, and dependencies.
debt
A command for showing and closing unanswered questions attached to project documents such as requirements, specifications, features, and designs. It can show questions for the whole project or for one document.
pr
A command for managing pull requests on GitHub or Bitbucket Server. A pull request is a request for other developers to review and merge changes into a project branch.