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 hatawong/claude-recap --skill save-topicgit clone --depth 1 https://github.com/hatawong/claude-recapWrote 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/hatawong/claude-recap/save-topic)<a href="https://agentmods.dev/skills/hatawong/claude-recap/save-topic"><img src="https://agentmods.dev/badge/skills/hatawong/claude-recap/save-topic.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 | $0.00029 | $0.00657 |
| Opus 5 | $0.00015 | $0.00329 |
| Sonnet 5 | $0.00006 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
save-topic 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- save-topic — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
save-topic
Overview
Saves a structured summary of a topic to a persistent file. Supports saving the current topic, a specific topic by slug, or multiple topics at once.
Instructions
Preparation
-
Get the session ID from the SessionStart injection in your context:
[SessionStart] session=SESSION_ID source=... -
Get the plugin scripts path from the SessionStart injection:
Plugin scripts path: /path/to/scripts -
Determine which topics to save:
- "save topic" / "checkpoint" → current topic only
- "save topic X" → the specified topic slug
- "save all topics" → all topics in this session
Saving the current topic
-
Get the current topic slug from your topic tag (the
› \slug`` you've been outputting). -
Write a structured summary using the format below (section headings in English, content in user's language, skip empty sections):
## Status
What was done, key progress.
## Decisions
What was chosen, why, what was rejected.
## Failures
What was tried, why it failed, the fix or workaround.
## Next Steps
What to do next. Be specific and actionable.
- Run:
bash "<plugin_scripts_path>/save-topic.sh" "<slug>" "<session_id>" "<summary>"
Saving a non-current topic
For topics you are NOT currently discussing, your LLM context is likely incomplete. Use the --cold flag to force cold-read from JSONL:
bash "<plugin_scripts_path>/save-topic.sh" --cold "<slug>" "<session_id>" ""
The script will extract the conversation from JSONL and generate a summary via claude -p. The third argument (summary) is ignored when --cold succeeds.
Saving multiple topics
- Get all topic slugs by running extract-topic.js (same as list-topics skill step 4):
node "<plugin_scripts_path>/extract-topic.js" "$HOME/.claude/projects/<project_id>/<session_id>.jsonl" __all__Filter out__untagged__from the output. - Save the current topic using the normal path (LLM writes summary).
- Save each non-current topic using the
--coldflag.
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.
- 7d ago First seen · 79 lines · 29 tokens per session scan A 520b6ae762a2
save-topic is a skill published in the GitHub repository hatawong/claude-recap (39 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 657 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.
Other skills, from other repositories
memory-write
Captures a durable fact to project memory through the kit's safe write path (PoisonGuard secret/injection screening + home-path sanitization + dedup + conflict detection) — preferring the cmk MCP tools (mkremember / mkforget / mktrust) when connected, falling back to the cmk CLI. Use when the user says "remember…
bootstrap
Scaffolds the core-memory-kit directory structure (context/, scripts/, cron/jobs/) into the current project. Idempotent — never overwrites existing files. Run once per project after installing the plugin. Use when the user says "bootstrap the memory system", "set up memory here", or "scaffold the memory kit".
troubleshooting
Diagnoses and repairs core-memory-kit itself when the memory system is broken — the per-failure-code repair book. Fire whenever a "⚠ [core-memory-kit]" whisper appears on the prompt (it names the failure and points here), or when the user reports a kit symptom however they phrase it: memory is not being saved, nothing…
memory-search
Searches the project's recorded memory (core-memory-kit) — decisions, conventions, architecture, the reasoning behind choices, and where things live — and returns a curated, cited summary. Fire whenever the answer might be something the project already established in past work, HOWEVER the question is phrased — any…
mem9
Persistent cloud memory for OpenClaw agents. Use when users say: "install mem9" "setup memory" "add memory plugin" "openclaw memory" "mem9 onboarding" "memory not working" "import memories" "upload sessions".
mem9
Persistent cloud memory for OpenClaw agents. Use when users say: "install mem9" "setup memory" "add memory plugin" "openclaw memory" "mem9 onboarding" "memory not working" "import memories" "upload sessions".