capture

A command for saving a decision, lesson, recurring pattern, or project context in persistent memory. It can infer a category or let you choose one explicitly.

In plain words
What is it for?
Use it to record technical decisions, lessons learned, rules of thumb, constraints, or future cleanup items.
Why use it?
It prevents useful project knowledge from being lost between conversations or coding sessions.

Command

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.

agentmods
npx agentmods add commands/zircote/subcog/capture
Clone the repo
git clone --depth 1 https://github.com/zircote/subcog
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00016 $0.00540
Opus 5 $0.00008 $0.00270
Sonnet 5 $0.00003 $0.00108
Haiku 4.5 $0.00002 $0.00054

Measured 2d ago against content hash 3afb88f1516e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

commands/capture.md · 74 lines

What it actually says

/subcog:capture

Capture decisions, learnings, patterns, and context as persistent memories.

Usage

/subcog:capture "Use PostgreSQL for primary storage"
/subcog:capture --namespace decisions "Chose Rust for single-binary distribution"
/subcog:capture --interactive

Arguments

Execution Strategy

Namespace Detection: If no namespace specified, detect from signal words:

  • "decided", "chose", "going with" → decisions
  • "always", "never", "when X do Y" → patterns
  • "TIL", "learned", "gotcha" → learnings
  • "because", "constraint" → context
  • "TODO", "FIXME", "temporary" → tech-debt

Interactive Mode

Examples

Explicit namespace:

/subcog:capture --namespace decisions "Use thiserror for custom error types in library code"

Interactive mode:

/subcog:capture --interactive

Will prompt for namespace, content, context, and tags.

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. 2d ago First seen · 74 lines · 16 tokens per session scan A 3afb88f1516e

Subscribe to this mod's changes

capture is a command published in the GitHub repository zircote/subcog (28 stars, last pushed 29d ago), licensed MIT. It adds 16 tokens to every session and 540 once invoked, about $0.0001 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.