A project-level tracking sheet that lists each specification row, its guard, related files and tags, and whether the work is complete. Completed rows are moved into a log.

It helps track project specifications, record comments or check marks on results, and keep completed work in a separate history.

It gives people a readable view of what has been done and what remains, instead of mixing project work with individual prompt requests.

project — Skill for Claude Code and Codex by wiber/thetacog-mcp

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 wiber/thetacog-mcp --skill project

Clone the repo

git clone --depth 1 https://github.com/wiber/thetacog-mcp

Made for: Claude Code, Codex.

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/wiber/thetacog-mcp/project/github.svg)](https://agentmods.dev/skills/wiber/thetacog-mcp/project)

Your own site

<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/project"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/project/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/wiber/thetacog-mcp/project"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,404 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	$0.00166	$0.01404
Opus 5.5	$0.00066	$0.00562
Sonnet 5.5	$0.00033	$0.00281
Haiku 4.5	$0.00017	$0.00140

Measured 5d ago against content hash 278b9560ee79, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project 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 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.

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.

skills/project/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/project — the project level, one above the prompt level

Operator 2026-10-30, verbatim: "we need a check box or a comment on how it went for the spec written, and it needs to be always called by the sear when we enable it so this is sort of like the second incentive project level, not the prompt level" · "the left offer part of it needs to be absolutely legible for a human to see what has been done over what is next" · "move the completed Rose to the lawn section right that's something we should be able to not generate actually program".

The prompt level is Steer · Compiled (board-steer.mjs): every dictation's asks. The project level is this: the rows a project holds until they are done. Both are spec rows; nothing here is typed by a model.

The sheets

sheet	built by	rows
Project · GTM	`node scripts/ops/board-project.mjs --project gtm`	every C-row `docs/specs/vna/gtm-spec.json` cites, plus every row tagged `(GTM: …)`
Project · Code	`node scripts/ops/board-project.mjs --project code`	the goal's units, the compiled steer's asks, rows declared in the last 7 days with a guard; GTM rows excluded; done rows kept 7 days
Spec · Tree	`node scripts/ops/board-tree.mjs`	every node of `data/vna/spec-tree.json`, root first, with its LEAF and the project sheet that holds it

The selection lives in docs/specs/vna/projects.json. A new project is a new entry there, never a new script.

Columns, left to right: ID · HOW IT WENT · YOUR COMMENT (fill) · OK? ✓ / ✗ (fill) · STATE (✓ DONE · ☐ NEXT · ✋ YOUR ACT · ✋ NEEDS YOU) · WHAT · NEXT STEP or the commit that ticked it · GUARD · FILES · TAGS · LEAF. The first five carry the reading; the rest are the references.

The move is a program, never tokens. The NEXT block sits on top by priority (data/vna/board-heads.ndjson). The pass after a row's tick lands, the row composes under DONE · LOG, and his cells move with it (the writer keys a typed cell by id and header). The move is ledgered first (data/vna/project-moves.ndjson), then appended to the sheet's Log tab.

Read the full file on GitHub · 43 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.

5d ago First seen · 43 lines · 166 tokens per session scan A 278b9560ee79

Subscribe to this mod's changes

project is a skill published in the GitHub repository wiber/thetacog-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 166 tokens to every session and 1,404 once invoked, about $0.0007 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 2026-11-02.

AI Safety LLM Planning Project management agentic determinism insurance mcp

project next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
projectwiber/thetacog-mcp	Skill	1	yesterday	MIT	A	166	Claude Code, Codex
git-checkpointagentscope-ai/agentscope-java	Skill	6.3k	today	Apache-2.0	A	39	Claude Code, Codex
synthesize-reportagentscope-ai/agentscope-java	Skill	6.3k	today	Apache-2.0	A	29	Claude Code, Codex
data-analysisagentscope-ai/agentscope-java	Skill	6.3k	today	Apache-2.0	A	25	Claude Code, Codex
summarizeragentscope-ai/agentscope-java	Skill	6.3k	today	Apache-2.0	A	24	Claude Code, Codex
agent-browserTencent/WeKnora	Skill	37k	4d ago	none	A	83	Claude Code, Codex
skill-creator-primersammcj/agentic-coding	Skill	169	3d ago	Apache-2.0	A	74	Claude Code