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 wiber/thetacog-mcp --skill tendgit clone --depth 1 https://github.com/wiber/thetacog-mcpWrote 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/wiber/thetacog-mcp/tend)<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/tend"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/tend/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/wiber/thetacog-mcp/tend"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/tend.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 | $0.00106 | $0.03640 |
| Opus 5.5 | $0.00042 | $0.01456 |
| Sonnet 5.5 | $0.00021 | $0.00728 |
| Haiku 4.5 | $0.00011 | $0.00364 |
Grade A, and why
Tend 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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tend — the sheets stay true, and the aim stays high
Operator 2026-10-20, verbatim: "how can we make a skill that uses /steer to go through all sheets and keep them reasonable and consistent (with the best possible, to the limit aggressive) outcome.."
The two forces held together: reasonable and consistent means every number, date and status on a sheet is one the record holds. To the limit aggressive means the aim line (kind aim in docs/specs/vna/days180-events.json) is the target the work is measured against. An aim is never lowered to fit the evidence. When the evidence trails an aim, the gap becomes a row that closes it. An aim moves only on his word.
What the pass is for: coherence on three axes, then the skim (operator 2026-10-24)
Verbatim: "make things more cohesive, coherence and consistent across time scales and across categories … think of the skill command as a way to create coherence and then skim the cream of the Top with the flow chart."
- Across time scales. Every row names the horizon it serves (
→ H-NN), and the Horizons chain runs backwards from 1000 years to today with no gap (R2). A row naming no horizon has no question it is sufficient for (AXIOM 1 W6): the pass names it, never ranks it. - Across categories. A ticket is formulated in ONE place, its HOME (the sheet whose ID column carries it, or the spec), and every other sheet shows it by id and links home. Never a second copy of its text (P1, P6). A ticket ticked at home leaves every NOW sheet in the same pass.
- The skim. The cream is the open threads with the widest reach across categories and the nearest horizon. It feeds THE TOP, where START HERE's flowchart ends (F-14, ≤10 decision-ready rows, C1030). The cream is read off the threads, never chosen by feel.
- His words leave the sheet in the same pass that acts on them. A held word (its row STUCK, open or never declared) is listed with its gate, and this pass works that row itself: it edits the source, ticks the row with its commit, then closes the word to the Log. A STUCK row is never left for a runner that already refused it twice.
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.
- 8d ago First seen · 84 lines · 106 tokens per session scan A e8b75a3e4fc3
Tend is a skill published in the GitHub repository wiber/thetacog-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 3,640 once invoked, about $0.0004 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 2026-10-30.
Tend compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Tendwiber/thetacog-mcp | Skill | 1 | yesterday | MIT | A | 106 | 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 |