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 tetracoralla/decision-table --skill use-decision-tablegit clone --depth 1 https://github.com/tetracoralla/decision-tableWrote 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/tetracoralla/decision-table/use-decision-table)<a href="https://agentmods.dev/skills/tetracoralla/decision-table/use-decision-table"><img src="https://agentmods.dev/badge/skills/tetracoralla/decision-table/use-decision-table/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/tetracoralla/decision-table/use-decision-table"><img src="https://agentmods.dev/badge/skills/tetracoralla/decision-table/use-decision-table.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 | $0.00074 | $0.00461 |
| Opus 5 | $0.00037 | $0.00230 |
| Sonnet 5 | $0.00015 | $0.00092 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
use-decision-table 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.
What it actually says
Use Decision Table
Move a bounded business judgment into the deterministic tools. Do not read the rules and reproduce their logic in prose or model reasoning.
Choose the tool
- Call
decision.evaluatewhen explicit facts must produce a business result. - Call
decision.validatewhenever a decision or constraint ruleset is new or changed, and before trusting it in an execution path. - Call
constraint.checkfor a proposed action or candidate configuration. - Call
constraint.check_approvedwhen the host exposes a pinned approved ruleset and the user needs a read-only check. The caller still supplies the candidate and facts; do not describe this as enforcement.
The selected tool exposes the complete current schema. Do not invent fields or convert prose into a ruleset unless the user asked to author policy.
Handle the result
- On
decided,valid, orvalid_with_warnings, present the business result, material warnings, and ruleset version concisely. - On
insufficient_input, obtain only the named missing facts from an authorized source and call the same tool again. Never treat missing as false. - On
conflict,invalid_ruleset,inactive_ruleset,version_mismatch, orfingerprint_mismatch, stop the governed action and ask the ruleset owner to resolve the named issue. - On
invalid, do not execute the candidate. Apply a repair hint only when the requested change is independently authorized, then re-check.
All tools are read-only. This Skill improves routing but cannot enforce policy. Do not authorize a governed side effect from either constraint tool alone. Real enforcement requires the host library guard to derive the candidate from the actual pending action, load trusted facts, and execute that same action snapshot only after a valid check.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 41 lines · 74 tokens per session scan A 3eb4c9fc1a8b
use-decision-table is a skill published in the GitHub repository tetracoralla/decision-table (0 stars, last pushed 10d ago), licensed Apache-2.0. It adds 74 tokens to every session and 461 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ui-context
A tool for reading the desktop window, interface element or screen area that a user selects with Little Mouse Pointer.
mindraw-open-canvas
Open the Mindraw canvas for this project. Use when the user asks to open, view, inspect, or edit the Mindraw project canvas from Codex.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.