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 punt-labs/quarry --skill quarry-capturegit clone --depth 1 https://github.com/punt-labs/quarryWrote 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/punt-labs/quarry/quarry-capture)<a href="https://agentmods.dev/skills/punt-labs/quarry/quarry-capture"><img src="https://agentmods.dev/badge/skills/punt-labs/quarry/quarry-capture/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/punt-labs/quarry/quarry-capture"><img src="https://agentmods.dev/badge/skills/punt-labs/quarry/quarry-capture.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 | $0.00189 | $0.00937 |
| Opus 5.5 | $0.00076 | $0.00375 |
| Sonnet 5.5 | $0.00038 | $0.00187 |
| Haiku 4.5 | $0.00019 | $0.00094 |
Grade A, and why
quarry-capture 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 24d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quarry Capture
Three verbs, three distinct jobs. Pick the one that matches what actually happened, not the one that's easiest to reach for.
Verb taxonomy
remember— one durable, agent-scoped item: a fact, a procedure, an opinion, or an observation. Filed under anagent_handle, findable later by that handle or by anyone searching broadly.learn— a distilled lesson the whole project should follow (a rule, a convention, a "do it this way" insight). No handle — it's project-wide, not personal — and it gets retrieval preference over ordinary results.ingest— a URL. Fetches and indexes it (sitemap-aware, single-page fallback). For local files or directories already on disk, useregister_directory+sync, notingest.
Recognize the trigger and the five moments
Call remember (or learn) at these moments — not at the end of a session,
and not never:
- You found a non-obvious root cause or gotcha →
remember,memory_type=fact. - A decision was ratified, with its reason →
remember,memory_type=fact. - You worked out a repeatable how-to →
remember,memory_type=procedure. - You formed a judgement you'll want to revisit →
remember,memory_type=opinion. - Once, before submitting a mission result — one note on what you'd tell
yourself next time →
remember,memory_type=observation.
Separately: when the insight is a rule the whole team/project should
follow, not just your own note-to-self → learn instead of remember.
Run it
printf '%s' "<content>" | quarry remember --name <topic-slug> \
--agent-handle <your-handle> --memory-type fact --summary "<one line>"
quarry learn "<lesson, <=500 chars>" [--topic <domain>] [--name <slug>]
quarry ingest <url> [--overwrite] [--collection <name>]
remember reads its content from stdin, not a positional argument — pipe
it in.
Confirm the exact flags with quarry remember --help / quarry learn --help / quarry ingest --help before relying on one not shown here.
What ships with it
1 file 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.
- 24d ago First seen · 86 lines · 189 tokens per session scan A 56a0c5edb063
quarry-capture is a skill published in the GitHub repository punt-labs/quarry (6 stars, last pushed yesterday), licensed MIT. It adds 189 tokens to every session and 937 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-22.
Other skills, from other repositories
autosearch:experience-compact
Promote recurring patterns from experience/patterns.jsonl into the compact experience.md digest (≤120 lines, read by runtime AI before calling the skill). Triggers on N-events / file-size / user-feedback / session-end. Guards against single-success noise and pollution via promotion thresholds.
autosearch:context-retention-policy
Session-level policy for keeping the runtime AI's context window healthy across long research — keep-last-k tool results, offload older evidence to disk, trigger compaction at thresholds. Borrows MiroThinker's keeptoolresult, deepagents' summarization middleware, and deer-flow's SummarizationEvent pattern. Orthogonal…
pond
Recall and analyze past AI agent sessions (Claude Code, Codex, opencode, and more). Find prior work and decisions, read/review/summarize a past session transcript, or run SQL analytics over session history. Use whenever the user references past sessions, prior work, "check pond", or asks what was done or decided…
stats
Show Captain Memo's corpus statistics (chunks per channel, observation counts, indexing progress, embedder info). Use when the user types /captain-memo:stats.
search
Hybrid search across Captain Memo's local memory + skills + observations. Use when the user types /captain-memo:search to retrieve top hits without the model having to decide whether to call searchall on its own.
doctor
Health probe across the worker, embedder, summarizer, queue, vector index, schema, cross-AI wiring and plugin install (cache and live versions). Use when the user types /captain-memo:doctor or when something seems wrong.