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 agentmods add commands/gosha70/code-copilot-team/promote-lessongit clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote 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/commands/gosha70/code-copilot-team/promote-lesson)<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/promote-lesson"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/promote-lesson.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00538 |
| Opus 5 | $0.00000 | $0.00269 |
| Sonnet 5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
promote-lesson 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 4d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote a session-level lesson into the project wiki at knowledge/wiki/. Follows the canonical curator procedure; never edits the wiki without it.
When to use this
The user has identified a lesson, decision, or recipe that should outlive the current session and wants it captured in the durable knowledge layer. Examples:
- "Document this incident — we should not repeat it."
- "This recipe for X should be a playbook."
- "Capture the rationale for choosing Y over Z."
If the user is asking you to remember something for this session only, use session memory instead. The wiki is for content that survives across sessions and contributors.
Argument
$ARGUMENTS — a brief description of the lesson to promote. Free-form prose. If empty, ask the user for a description before proceeding.
Procedure
-
Read the curator persona. Open and follow
knowledge/wiki/schema/WIKI_MAINTAINER.mdin full. Do not skip this even if you have run this command before — the schema can change. -
Apply the four-question gate from
knowledge/wiki/schema/ingest-rules.md. If the lesson does not qualify, tell the user why it does not qualify and stop. Do not promote a borderline lesson "to be safe". -
Walk the canonical loop from
knowledge/wiki/workflows/promote-lesson-to-wiki.mdend-to-end:- Pick the page type (
knowledge/wiki/schema/page-types.md). - Pick or reuse the slug.
- Gather sources per
knowledge/wiki/schema/citation-rules.md(no source → no page). - Write or update the page using the type's template.
- Link from
knowledge/wiki/index.md. - Append a one-line entry to
knowledge/wiki/log.md.
- Pick the page type (
-
Run the linter:
bash knowledge/wiki/scripts/lint-wiki.shIf it fails, fix the violation. Never commit lint violations and never silence the linter.
-
Stop. Do not "improve" adjacent pages in the same turn. Drive-by edits make review hard. If the user wants more lessons promoted, run this command again per lesson.
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.
- 4d ago First seen · 44 lines · 0 tokens per session scan A 7947f07fca90
promote-lesson is a command published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 538 tokens. 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 commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".
setup-bigquery.es
Command "setup-bigquery.es" from minicoohei/ai-agent-camp, covering configuración de autenticación bigquery / gcp, step 0: verificar el progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: instalación de gcloud cli.
setup-content
Lesson command — 教材コンテンツの初回セットアップ.