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 somnus0x/agt-skill-pack --skill decision-decaygit clone --depth 1 https://github.com/somnus0x/agt-skill-packWrote 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/somnus0x/agt-skill-pack/decision-decay)<a href="https://agentmods.dev/skills/somnus0x/agt-skill-pack/decision-decay"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/decision-decay/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/somnus0x/agt-skill-pack/decision-decay"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/decision-decay.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 | $0.00045 | $0.01016 |
| Opus 5.5 | $0.00018 | $0.00406 |
| Sonnet 5.5 | $0.00009 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
decision-decay 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 1mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Decay — When Past Decisions Go Stale
Decisions are perishable. A choice that was correct in January may be wrong in March — not because the reasoning was flawed, but because the inputs changed. This skill detects when the world has moved and a past decision hasn't moved with it.
The Decay Model
Every decision rests on assumptions about the world. When those assumptions change, the decision decays.
| Stage | Signal | Action |
|---|---|---|
| Fresh | Assumptions still hold. No contradicting evidence. | No action needed. |
| Aging | One+ supporting assumptions weakened but not invalidated. | Flag for review within 2 weeks. |
| Stale | Core assumption invalidated. Better alternatives exist. Staying costs more than switching. | Active re-evaluation. |
How to Use
Step 1: Log your decisions
Keep a simple decision log (Notion, Obsidian, markdown file, whatever you use). Each entry needs:
- What you decided and what you chose it over
- Date
- Why — the reasoning at the time
- Review date — when to check if it still holds
Example:
DEC-001: Use Firebase over Supabase
Date: 2026-01-15
Chose: Firebase over Supabase
Why: Firebase Auth has better mobile SDK, team has Firebase experience, real-time listeners are simpler
Review: 2026-04-15
Step 2: Extract the assumptions
For each decision, identify what had to be true for it to be correct. Usually 2-4 core assumptions.
For the example above:
- Firebase Auth mobile SDK is better than Supabase Auth
- Team has Firebase experience (reduces ramp-up)
- Real-time listeners are simpler in Firebase than Supabase Realtime
Step 3: Check assumptions against current reality
Use whatever signals you have — ecosystem news, GitHub activity, your own experience, competitor moves.
Step 4: Score the decay
- All assumptions hold → Fresh → No action
- 1+ weakened → Aging → Review soon
- Core assumption broken → Stale → Re-evaluate now
Output Format
What ships with it
3 files 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.
- 1mo ago First seen · 121 lines · 45 tokens per session scan A 3a727d84ccb0
decision-decay is a skill published in the GitHub repository somnus0x/agt-skill-pack (74 stars, last pushed 18d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,016 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…