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 riekelt/technical-writer --skill recording-decisionsgit clone --depth 1 https://github.com/riekelt/technical-writerWrote 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/riekelt/technical-writer/recording-decisions)<a href="https://agentmods.dev/skills/riekelt/technical-writer/recording-decisions"><img src="https://agentmods.dev/badge/skills/riekelt/technical-writer/recording-decisions.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00068 | $0.00931 |
| Opus 5 | $0.00034 | $0.00465 |
| Sonnet 5 | $0.00014 | $0.00186 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
recording-decisions 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 7d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recording decisions
REQUIRED BACKGROUND: the technical-writing skill (hard rules, truth rules, style).
Overview
Two formats, by weight. A full ADR for a decision with architecture-level consequences; a decision log entry for the running stream of smaller choices. Both are append-only: an accepted decision is immutable, and new context is a new entry that supersedes the old one.
When to invoke, and not
Invoke when a choice has been made and needs recording, when someone asks "write down why we did this", or when an existing decision is superseded. Do NOT invoke for a decision still being argued (that is writing-design-docs; the Why & What box becomes the ADR once accepted).
Also invoke on the signals that an unrecorded decision is passing by: "we decided X instead of Y", "let's just go with", a trade-off resolved in a PR comment or chat thread, or a rationale someone has now explained twice. Each of those is a decision living in a non-durable place; offer to record it.
Record the decision before citing it. A chat session is not a durable source. Put the dated substance in the log and quote the decider where wording matters, then commit the entry before citing it. Record the smallest complete decision, not a transcript.
ADR
Nygard format. One decision per ADR.
# ADR-[number]: [short title of the decision]
| | |
|---|---|
| **Status** | Proposed / Accepted / Superseded by ADR-XXX |
| **Date** | YYYY-MM-DD |
| **Deciders** | [who took part] |
## Context
[The forces at play: technical, organizational, political. What must be solved.
Factual, without giving away the decision.]
## Decision
[What was decided. Active voice: "We release on tags", not "it was decided that".]
## Consequences
**Positive:** [what gets easier]
**Negative:** [what gets harder, which trade we accept]
**Neutral:** [what changes without being better or worse]
## Alternatives considered
**[Alternative]** - For: [...] Against: [...] Why not chosen: [...]
## References
[Evidence, related decisions, measurements]
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.
- 7d ago First seen · 82 lines · 68 tokens per session scan A 07dfb3f84e99
recording-decisions is a skill published in the GitHub repository riekelt/technical-writer (15 stars, last pushed 8d ago), licensed MIT. It adds 68 tokens to every session and 931 once invoked, about $0.0003 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…