quarry-capture

quarry-capture is a skill for Claude Code from punt-labs/quarry. It costs 189 tokens per session (937 once invoked), scanned A, original, MIT.

A memory-saving procedure for storing durable facts, project lessons, decisions, procedures, and URLs in a searchable store called quarry. It distinguishes personal memories from rules meant for the whole project.

In plain words
What is it for?
Use it when someone asks to remember or save something, when you find a non-obvious cause, or when a project decision or repeatable procedure should be retained. It also handles indexing a URL for later retrieval.
Why use it?
Important discoveries and decisions can disappear when an agent's working context is shortened or a session ends. Saving them in the right form makes them available later instead of requiring the work to be repeated.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the quarry-dev plugin — 2 skills, 16 commands, 1 agent, 5 hooks shipped together

Good fit Use it when someone asks to remember or save something, when you find a non-obvious cause, or when a project decision or repeatable procedure should be retained. It also handles indexing a URL for later retrieval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/punt-labs/quarry/quarry-capture
Install

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.

Any agent
npx skills add punt-labs/quarry --skill quarry-capture
Clone the repo
git clone --depth 1 https://github.com/punt-labs/quarry

Made for: Claude Code.

Or install quarry-dev, the plugin that ships this one along with the rest of its 2 skills, 16 commands, 1 agent, 5 hooks.

Wrote 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.

agentmods badge for quarry-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/punt-labs/quarry/quarry-capture/github.svg)](https://agentmods.dev/skills/punt-labs/quarry/quarry-capture)
Your own site
<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.

agentmods 80×15 button for quarry-capture

Your own site · 80×15
<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>
Per session 189 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 937 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 24d ago against content hash 56a0c5edb063, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

plugin/skills/quarry-capture/SKILL.md · 86 lines

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 an agent_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, use register_directory + sync, not ingest.

Recognize the trigger and the five moments

Call remember (or learn) at these moments — not at the end of a session, and not never:

  1. You found a non-obvious root cause or gotcha → remember, memory_type=fact.
  2. A decision was ratified, with its reason → remember, memory_type=fact.
  3. You worked out a repeatable how-to → remember, memory_type=procedure.
  4. You formed a judgement you'll want to revisit → remember, memory_type=opinion.
  5. 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.

Read the full file on GitHub · 86 lines

Files

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.

Changes

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.

  1. 24d ago First seen · 86 lines · 189 tokens per session scan A 56a0c5edb063

Subscribe to this mod's changes

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.

Related

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.

0xmariowu/Autosearch · 69 tokens

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…

0xmariowu/Autosearch · 89 tokens

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…

tenequm/pond · 71 tokens

stats

Show Captain Memo's corpus statistics (chunks per channel, observation counts, indexing progress, embedder info). Use when the user types /captain-memo:stats.

kalinbogatzevski/captain-memo · 36 tokens

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.

kalinbogatzevski/captain-memo · 49 tokens

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.

kalinbogatzevski/captain-memo · 52 tokens