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 agentmods add skills/ai-swiss/base/decidenpx skills add ai-swiss/base --skill decidegit clone --depth 1 https://github.com/ai-swiss/baseWrote 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/ai-swiss/base/decide)<a href="https://agentmods.dev/skills/ai-swiss/base/decide"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/decide.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00641 |
| Opus 5 | $0.00017 | $0.00320 |
| Sonnet 5 | $0.00007 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
decide 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.
What it actually says
Decision sheet
When several choices are open, a sheet beats a chat thread: the human rates each point, comments, and exports them all in one pass. The human decides; the sheet structures the decision.
Steps
- List the real decisions. One card per point. Each card carries the context, your recommendation (lead with it), and where relevant your prior reading. Do not pad with already-settled items.
- Build from the template. Copy the agent's template at
.ai/agents/base-contributor/templates/decision-sheet.htmlto.temp/{YYYY-MM-DD}_{slug}/{YYYY-MM-DD}_{slug}_decisions.html— a dated stem, unique per sheet. Fill the title, intro, thePOINTSarray (id,title,what,reco,recoSummary,scaleLabel), and the two names that pair the blank with the return:STORAGE_KEY={YYYY-MM-DD}_{slug}_decisions(namespaces the browser autosave) andEXPORT_FILE={YYYY-MM-DD}_{slug}_decisions-filled.md(so the export sorts next to its blank and stays self-describing outside the folder). - Keep it clean. No reference to any external framework or banned phrasing; AI Swiss styling
is already in the template.
.temp/is gitignored, so the sheet stays scratch. - Open it for the human and wait. The sheet auto-saves to the browser, and the export is a Markdown file the human hands back.
- Act on the export. Apply where they agree, follow their comments where they nuance, keep
your recommendation where they did not answer (and say so). Durable choices graduate to an
open-changerecord.
What you never do
- Decide on the human's behalf, or turn an honest abstention into a forced choice.
- Re-litigate points already settled, or bury the recommendation under context.
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 · 55 lines · 35 tokens per session scan A 63f86161fc5b
decide is a skill published in the GitHub repository ai-swiss/base (42 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 641 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
achieving-cmmc-level-2-compliance
Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when…
escalation-governance
Assess whether to escalate models. Use when evaluating reasoning depth.
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
wallet-cli
Operate the TypeScript TRON wallet CLI for accounts, transfers, staking, governance, contracts, signing, chain queries, and password input with wallet-cli 4.12.0. Refuse wallet passwords in argv and require the supported stdin channel. For Java REPL requests, refuse that entry and offer the TypeScript one-shot CLI…
TRX Staking & SR Voting
Stake TRX, vote for Super Representatives, and claim voting rewards on TRON.
digital-native-governance-check
Assess Azure governance maturity for Digital Natives and startups. Detects the most common anti-patterns from the "Digital Natives on Azure" series: incomplete Service Health alerts, flat subscription topology without Management Groups, excessive RBAC (everyone is Owner), missing budget alerts, no Managed Identity…