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/initialneil/project-with-reflect/record-a-lessongit clone --depth 1 https://github.com/initialneil/project-with-reflectWrote 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/initialneil/project-with-reflect/record-a-lesson)<a href="https://agentmods.dev/commands/initialneil/project-with-reflect/record-a-lesson"><img src="https://agentmods.dev/badge/commands/initialneil/project-with-reflect/record-a-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 | $0.00032 | $0.00500 |
| Opus 5 | $0.00016 | $0.00250 |
| Sonnet 5 | $0.00006 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
record-a-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.
What it actually says
Run the record action of the current project's project-with-reflect skill with arguments: $ARGUMENTS
Resolve the project from the current directory first: match $PWD against registry.json projects'
repo / dir (the project whose repo or state dir contains $PWD). If none matches, ask which
project — don't guess. (Same cwd→registry match /log-and-reflect and the auto-log hook use.) Then
follow <project_dir>/SKILL.md's record action.
record persists a durable thing to permanent memory now — distinct from note (an ephemeral
log line) and reflect (the end-of-session sweep). It's flexible (not experiment-specific): infer or
take the kind and land it in the right flat lessons/<descriptive>.md — most often by
updating / editing / appending an existing lesson, a new file only when nothing fits —
- result / benchmark / eval report → a record lesson (
lessons/experiment-GUAVA.md) — accumulates, append-only; - rule / must-follow practice / settled conclusion → a distilled lesson (
lessons/<topic>.md, bounded) +decisions.mdif it's a decision; - reference / resource / link → a notes lesson (
lessons/resources.md), or the globalknowledge/<k>(/register-knowledge+use-knowledge) if broadly reusable; - research report / review / etc. → its own lesson; anything else durable → the closest fit.
If it continues an existing lesson, follow that lesson's established format (its sections / columns /
artifact embedding) so entries stay uniform and comparable — for any kind, not just experiments. One
thing → its home; archives nothing. Use it the moment a durable result lands, or when the user says
"record <X>" (optionally "as a <kind>").
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 · 28 lines · 32 tokens per session scan A 2141695b8351
record-a-lesson is a command published in the GitHub repository initialneil/project-with-reflect (13 stars, last pushed 15d ago), licensed MIT. It adds 32 tokens to every session and 500 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 commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
neo-review
Get Neo's code review with semantic matching against past findings in memory. Use on a diff or module before merge, especially where earlier mistakes in this codebase are likely to recur. Skip for formatting, lint-catchable issues, and single-line changes.