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 harnessprotocol/harness-kit --skill capturegit clone --depth 1 https://github.com/harnessprotocol/harness-kitWrote 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/harnessprotocol/harness-kit/capture)<a href="https://agentmods.dev/skills/harnessprotocol/harness-kit/capture"><img src="https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/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.
<a href="https://agentmods.dev/skills/harnessprotocol/harness-kit/capture"><img src="https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.00997 |
| Opus 5.5 | $0.00029 | $0.00399 |
| Sonnet 5.5 | $0.00015 | $0.00199 |
| Haiku 4.5 | $0.00007 | $0.00100 |
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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Staging
Overview
Capture information from the current conversation into a staging file for the daily reflection pipeline to consume and write to the knowledge graph.
Core principles:
- Token-conscious — 3-8 bullets, max 20 words each
- Complementary to Stop hook — captures nuance and specificity the auto-summary misses
- Append-only — never modify existing entries in the staging file
- Confirm what was staged — always show the user exactly what was written
Argument Types
| Argument | Behavior |
|---|---|
| (none) | Auto-extract 3-8 most important facts from the conversation |
| Specific text | Stage the provided facts as bullets |
decisions |
Extract only decisions made this session |
technical |
Extract only technical facts and implementation details |
Workflow (MANDATORY — follow in order)
Step 1: Parse Input
Classify the argument:
- No argument → auto-extract mode
- Exactly the word
decisions→ filter to decisions only - Exactly the word
technical→ filter to technical facts only - Anything else → treat as specific facts provided by the user
Step 2: Resolve Staging File
Check in order:
scripts/session-staging.mdin the project root (current working directory)~/.claude/session-staging.mdas fallback
If the resolved file does not exist, create it with this header:
# Session Staging
Facts staged here are consumed by the daily reflection and written to the knowledge graph.
Step 3: Extract or Formulate Bullets
Based on argument type, produce 3-8 bullets. Each bullet: max 20 words, factual, specific.
Auto-extract (no argument): Scan the conversation for the most important facts — decisions made, technical details learned, status changes, new entities or tools introduced. Prefer concrete facts over vague summaries.
Specific facts (user-provided text): Convert the user's text into clean bullet points. If they already gave you bullets, clean and tighten them. If they gave you prose, extract the key facts.
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.
- 1mo ago First seen · 105 lines · 73 tokens per session scan A ca96a94da504
capture is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 997 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…