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/jketreno/clare/distillgit clone --depth 1 https://github.com/jketreno/clareWrote 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/jketreno/clare/distill)<a href="https://agentmods.dev/commands/jketreno/clare/distill"><img src="https://agentmods.dev/badge/commands/jketreno/clare/distill.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 5.1 | $0.00000 | $0.00517 |
| Opus 5 | $0.00000 | $0.00259 |
| Sonnet 5 | $0.00000 | $0.00103 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
distill scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
RESPONSE=$(curl -sf -X POST "${PIPELINE_URL}/distill/trigger" \ What it actually says
/project:distill — Trigger an on-demand CLARE₂ distillation pass
Sends a distillation request to the CLARE₂ pipeline container, which processes today's session files and writes extracted patterns to the episode store. Can be run any time; the nightly cron also runs at 22:00 UTC automatically.
Instructions
AI_VLLM_ROOT="${CLARE2_ROOT:-../ai-vllm}"
PIPELINE_URL="${CLARE2_PIPELINE_URL:-http://127.0.0.1:8000}"
TOKEN_FILE="${CLARE2_OPERATOR_TOKEN_FILE:-${AI_VLLM_ROOT}/secrets/clare2_operator_token}"
TOKEN=$(<"${TOKEN_FILE}")
# Trigger the distillation pass
RESPONSE=$(curl -sf -X POST "${PIPELINE_URL}/distill/trigger" \
-H "Authorization: Bearer ${TOKEN}" \
-H "Content-Type: application/json" 2>&1)
if [[ $? -ne 0 ]]; then
echo "❌ Could not reach the CLARE₂ pipeline at ${PIPELINE_URL}"
echo " Is the pipeline container running?"
echo " Start it with: docker compose -f ${AI_VLLM_ROOT}/docker-compose.yml up -d clare2-policy"
exit 1
fi
echo "✅ Distillation pass triggered."
echo " The pipeline is processing today's sessions in the background."
echo ""
# Poll for status
sleep 5
STATUS=$(curl -sf "${PIPELINE_URL}/distill/status" \
-H "Authorization: Bearer ${TOKEN}" 2>/dev/null || echo '{}')
echo "Corpus stats:"
echo "$STATUS" | python3 -m json.tool 2>/dev/null || echo "$STATUS"
After running, report:
- Whether the pipeline accepted the request
- The current corpus stats (episodes by category, last distillation timestamp)
- If the pipeline is unreachable, how to start it
Notes
- Distillation is idempotent for the same day's sessions — re-running appends only new patterns that weren't already in the episode file.
- The recurrence gate (evidence_count ≥ 2) applies during distillation. Single-occurrence patterns are dropped.
- Full nightly schedule: distill at 22:00 → summarize at 22:30 → assemble corpus at 23:30 → train at 00:00 → new Temper live by 06:00.
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.
- 6d ago First seen · 52 lines · 0 tokens per session scan A 76d6044fcbc7
distill is a command published in the GitHub repository jketreno/clare (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 517 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.