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 robotaitai/project-bedrock --skill decision-recordinggit clone --depth 1 https://github.com/robotaitai/project-bedrockWrote 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/robotaitai/project-bedrock/decision-recording)<a href="https://agentmods.dev/skills/robotaitai/project-bedrock/decision-recording"><img src="https://agentmods.dev/badge/skills/robotaitai/project-bedrock/decision-recording/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/robotaitai/project-bedrock/decision-recording"><img src="https://agentmods.dev/badge/skills/robotaitai/project-bedrock/decision-recording.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00855 |
| Opus 5 | $0.00021 | $0.00428 |
| Sonnet 5 | $0.00008 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
decision-recording scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Recording
Persists the rationale for architectural and design choices so future agents do not re-litigate settled questions.
When to record a decision
Record when any of these occur:
- A technology, framework, or pattern is chosen over alternatives
- A structural constraint is adopted (e.g., "no ORM", "raw SQL only")
- A previous decision is reversed or superseded
- The user says "remember why we chose X" or "note that we decided not to do Y"
Do NOT record:
- Tactical choices (variable names, minor refactors, formatting)
- Facts that are obvious from reading the code
- Speculative decisions not yet confirmed
Step 1 -- Create the decision file
SLUG="<short-hyphenated-title>"
DATE=$(date +%Y-%m-%d)
FILE="agent-knowledge/Memory/decisions/${DATE}-${SLUG}.md"
Copy from templates/memory/decision.template.md.
Preserve YAML frontmatter.
Step 2 -- Fill in the template
Required fields -- keep each one short:
| Field | Content |
|---|---|
| What | One sentence: what was decided |
| Why | Primary driver: constraint, measurement, user preference |
| Alternatives considered | 1-3 bullets: what was rejected and why |
| Consequences | 1-3 bullets: what this locks in or rules out |
Optional:
- Superseded by: link to the reversal decision if this one is no longer active
Step 3 -- Link from the relevant branch note
In the relevant branch note under Memory/, add or update the Decisions section:
## Decisions
- [2025-01-15-use-raw-sql.md](decisions/2025-01-15-use-raw-sql.md) -- chose raw SQL over ORM
One line per decision. Keep descriptions under 10 words.
Step 4 -- Update decisions/decisions.md
Prepend a line in agent-knowledge/Memory/decisions/decisions.md:
- [2025-01-15-use-raw-sql.md](2025-01-15-use-raw-sql.md) -- chose raw SQL over ORM
Newest first. If the decision reverses an earlier one, add [reverses YYYY-MM-DD-slug].
Step 5 -- Update Memory/MEMORY.md if the root summary changed
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.
- 9d ago First seen · 125 lines · 42 tokens per session scan A 56b1a400f2e9
decision-recording is a skill published in the GitHub repository robotaitai/project-bedrock (45 stars, last pushed 20d ago), licensed MIT. It adds 42 tokens to every session and 855 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…