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 olegvg/olegvg-skills --skill kb-record-decisiongit clone --depth 1 https://github.com/olegvg/olegvg-skillsWrote 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/olegvg/olegvg-skills/kb-record-decision)<a href="https://agentmods.dev/skills/olegvg/olegvg-skills/kb-record-decision"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/kb-record-decision/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/olegvg/olegvg-skills/kb-record-decision"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/kb-record-decision.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 | $0.00072 | $0.01553 |
| Opus 5 | $0.00036 | $0.00776 |
| Sonnet 5 | $0.00014 | $0.00311 |
| Haiku 4.5 | $0.00007 | $0.00155 |
Grade A, and why
kb-record-decision 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 11d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kb-record-decision — Record Shipped Decisions from Completed Plans
When to use
A plan in docs/plans/<timestamp>/plan-<slug>.md (or similar) is complete — the work shipped, the checklist is ticked, the code reflects the decisions made. The user wants the durable choices preserved in the KB without carrying the operational noise of the plan itself.
Manual, on-demand. Never automatic. Never invoked by build.
Input
- Plan path — path to a completed plan file or its containing directory. If missing, ask.
Output
- One decision record at
.kb/decisions/<YYYY-MM-slug>.md. That is the only file this skill writes. - The source plan is left untouched. Never modify
docs/plans/. - The summaries listed in the record's
## Affected areasblock are not edited — they remain the agent's view of the present, the decision-record carries the link to them, not the other way around.kb-queryreaches a decision via that backreference (grep -l "<summary-path>" .kb/decisions/).
Workflow
1. Read the plan
Read <plan-path>. If a sibling checklist-*.md exists, read that too. Extract:
- What problem the plan was solving.
- What decision was made.
- What alternatives were considered and rejected.
- Which parts of the codebase / KB the decision affects.
For plans larger than ~1500 lines, do not read the whole file — see references/large-plan-strategy.md.
2. Confirm the plan is complete
Before recording, verify:
- Checklist items are all ticked (if a checklist exists):
grep -c '^- \[ \]' <checklist-path>returns 0. - Git log shows commits implementing the plan have landed.
If neither holds, stop. See references/failure-modes.md for the "plan not yet complete" path.
3. Draft the decision record
Use the shape and field rules in references/decision-template.md. Required fields:
- Date —
YYYY-MMonly. - Slug —
kebab-case, derived from the plan filename. - Decision — one or two sentences.
- Context — 2–5 sentences.
- Alternatives considered — one line per rejection.
- Consequences — what changes.
- Affected areas —
.kb/summaries/<area>/<leaf>.mdpaths this decision shapes. This list is the only linkage between the record and the summaries it affects. - Source plan — path to the original plan.
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.
- 11d ago First seen · 124 lines · 72 tokens per session scan A 423cb6f10979
kb-record-decision is a skill published in the GitHub repository olegvg/olegvg-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 1,553 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
engram
Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture only durable, high-value knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered…
engram-digest
Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…
bootstrap-llm-synthesis
Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.
memory-delta-triage
Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode. Activate when Discovery processes a raw memory-delta from contexts/artefacts/memory-deltas/.
memory-reconcile
Scan all memory files, documentation (/docs//.md), and README files (/README.md) for drift, contradictions, and stale references. Produce a reconciliation report for Discovery to action. Activate on demand or via cron.
memory-archive-superseded
Migrate a superseded DEC's index rows from active index.md to archive/superseded-decisions.archive.md. Idempotent. Discovery-only — never invoked by daemon delivery. Updates DEC frontmatter as canonical source of truth.