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 skills/ackeskin/contexture/capturenpx skills add AcKeskin/contexture --skill capturegit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/ackeskin/contexture/capture)<a href="https://agentmods.dev/skills/ackeskin/contexture/capture"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/capture.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 | $0.00100 | $0.04557 |
| Opus 5 | $0.00050 | $0.02278 |
| Sonnet 5 | $0.00020 | $0.00911 |
| Haiku 4.5 | $0.00010 | $0.00456 |
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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
capture
The capture organ. Writes stored memory for future discovery; the memory format and kind taxonomy live in the format spec below.
Prerequisite — load the format spec
Before classifying or writing anything, Read ~/.claude/claude-md/memory-capture.md (the frontmatter template, kind table, folder layout, and capture rules). It is not always-on context — it loads here, on demand, only when capture actually runs. Every reference to claude-md/memory-capture.md below assumes you have read it this turn.
When to run
- User types
/capture [content](explicit trigger). - User says "remember that…", "save this as a memory," "capture this lesson."
- Another skill invokes capture programmatically (e.g. review's user-correction feedback loop).
- High-stakes auto-propose. Claude proposes a capture unprompted — at the moment it happens, mid-session — when a genuinely high-stakes item surfaces: (a) a decision that reverses or supersedes a prior shipped decision; (b) a correction the user phrases with finality ("never do X again", "this is the rule now"); (c) a
kind: warning-shaped event ("I did X, it broke Z, hard to undo"). This is auto-propose, never auto-write — the standard accept/edit/reject (§7) still gates every write, so the collaborator principle holds. Fire on the event, not at session close — deferring to/recaploses it when no recap runs. Keep it rare: only the three shapes above; never auto-propose ordinary lessons. - Otherwise do not auto-fire. No session-start or per-turn triggers. Mode B (silent episodic auto-write) stays parked — see the auto-propose bullet above.
Inputs
- Content source.
- Text passed after
/capture→ that text is the candidate rule / lesson / fact. - No arguments → infer content from the most recent user/assistant turns. If multiple recent turns could be the capture target, ask one clarifying question rather than guessing.
- Text passed after
- Triggering context. What in the session made this worth capturing — a correction, a decision, a surprise, a pattern. Use this to decide
kindand to write the Why: line. - Target project.
$CLAUDE_PROJECT_DIRif set, otherwise current working directory. Universal-applicable content may override to the global tree (see §"Universal vs project" below).
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.
- 2d ago First seen · 236 lines · 100 tokens per session scan A dc8d5299ae11
capture is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 4,557 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
log-session
Append a structured entry to the project's session log (docs/LOGS.md): what was done this session, files touched, decisions taken, and the next step — so the next session (or another person) can pick up the thread without re-reading git history. Run it before /clear, before closing Claude Code, or at any natural…
context-scaffold
Analyzes an existing project and generates context files (AGENTS.md, context directory, cascading structure) pre-populated with discovered information. Run once to bootstrap, then customize.
ReasoningBank with AgentDB
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
V3 Memory Unification
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).
context-upgrade
Guides transition from your current context level to the next one -- minimal to full, full to cascading, or adding skills and hooks layers. Preserves existing content.