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/primeline-ai/evolving-lite/remembergit clone --depth 1 https://github.com/primeline-ai/evolving-liteWhat 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 | $0.00009 | $0.00511 |
| Opus 5 | $0.00005 | $0.00255 |
| Sonnet 5 | $0.00002 | $0.00102 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
remember 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 2d 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
Save an explicit memory/experience to the Evolving Lite knowledge base.
Input: $ARGUMENTS
If empty: "What should I remember? Describe what you learned, decided, or want to keep."
Process
-
Classify the type:
solution- How you solved a problemgotcha- A non-obvious pitfall or trappattern- A reusable approach or techniquetechnique- A specific method or tool usagedecision- An architectural or design decisionpreference- A user preference or convention
-
Extract key fields:
summary: One-line descriptionproblem: What was the context/challenge (if applicable)solution: What worked / what to dotags: 2-4 relevant keywords
-
Save as experience file: Write to
${CLAUDE_PLUGIN_ROOT}/_memory/experiences/exp-{timestamp}.json, where{timestamp}isYYYYmmdd-HHMMSS.If that file already exists, append
-2, then-3, until you find a free name (exp-20260317-143022-2.json). Thecorrection-detectorhook writes into the same directory on the same turn, so a plain timestamp will silently overwrite the experience it just saved - the exact loss this suffix exists to prevent. Theidfield inside the file must match the filename you chose. -
Confirm: "Saved: {summary} [type: {type}, tags: {tags}]"
Example
User: /remember "Always check tsconfig strict mode first when debugging TypeScript type errors"
Result:
{
"id": "exp-20260317-143022",
"type": "gotcha",
"summary": "Check tsconfig strict mode first for TypeScript type errors",
"problem": "TypeScript type errors that seem wrong or inconsistent",
"solution": "Check tsconfig.json strict mode setting before investigating individual type errors",
"tags": ["typescript", "debugging", "tsconfig"],
"confidence": 0.8
}
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.
- 2d ago First seen · 56 lines · 9 tokens per session scan A 4b9b7bfd1df9
remember is a command published in the GitHub repository primeline-ai/evolving-lite (48 stars, last pushed 15d ago), licensed MIT. It adds 9 tokens to every session and 511 once invoked, about $0.0000 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
stop
Run /summary → /capture → /learn, then either /compact or clear based on whether work remains.
consolidate
Dream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
optimize
Suggest concrete performance improvements for the given file or directory.
pr
Open a pull request from the current branch with a generated title and summary.