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 AcKeskin/contexture --skill recapgit 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/recap)<a href="https://agentmods.dev/skills/ackeskin/contexture/recap"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/recap.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 | $0.00090 | $0.03660 |
| Opus 5 | $0.00045 | $0.01830 |
| Sonnet 5 | $0.00018 | $0.00732 |
| Haiku 4.5 | $0.00009 | $0.00366 |
Grade A, and why
recap 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 4d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
recap
Session recaps are the second memory tier — episodic, per-session, structured. Rules (existing tier) answer how should I work; recaps answer what happened and where did I leave off. Format follows claude-md/memory-capture.md §"Folder layout" — type: session-recap, lands under memory/sessions/.
When to run
- User types
/recap [title](explicit trigger; title is optional). - User says "wrap up", "write session notes", "recap this session", "document what we did".
- Claude proposes a recap when the user signals session closure — e.g. "done for today", "that's it for now", a PR merge, a deliberate pause after a non-trivial chunk of work. Propose, don't write. User confirms before anything lands.
- Never fires automatically on time, event, or tool-use boundary. Mode B stays parked.
- The
clear-context-decision-guardhook may surface a recovery nudge at the start of a new session if the previous one was cleared/compacted while decisions sat unrecapped. That nudge routes here — propose a recap reconstructing the prior session's decisions from its on-disk transcript. A recap that writes asessions/*.mdfile is the guard's "persisted" watermark; once it runs, the guard goes quiet.
Inputs
- Session context. The current in-conversation transcript — what the user asked for, what Claude investigated / touched / shipped, what was learned that's worth future recall.
- Arguments after
/recap— optional short title for the recap. When omitted, Claude infers from the session's primary goal. - Working directory —
$CLAUDE_PROJECT_DIRorcwd. Determines which project's memory tree receives the recap. - The
--under-wrapsignal (set only whenwrapinvokes recap as part of the session-terminus ceremony). When present, recap suppresses its own §7.4 close/changelog doorways —/wrapowns those offers (its steps 4–5), so recap offering them too would double-offer. Everything else (gather, draft, write, §8 promotion, §9 bloat check) runs unchanged. Absent the signal (a standalone/recap), §7.4 fires as normal.
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.
- 4d ago First seen · 163 lines · 90 tokens per session scan A 8685a1beef81
recap is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 3,660 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.
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.
ReasoningBank Intelligence
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.