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 alivecontext/alive --skill capture-contextgit clone --depth 1 https://github.com/alivecontext/aliveWrote 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/alivecontext/alive/capture-context)<a href="https://agentmods.dev/skills/alivecontext/alive/capture-context"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/capture-context/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/alivecontext/alive/capture-context"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/capture-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 54 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00074 | $0.03267 |
| Opus 5.5 | $0.00030 | $0.01307 |
| Sonnet 5.5 | $0.00015 | $0.00653 |
| Haiku 4.5 | $0.00007 | $0.00327 |
Grade A, and why
alive:capture-context 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture
Bring context in. The most important skill in the system.
If capture is hard, people skip it. If people skip it, the system dies. Capture must feel instant.
When It Fires
- File pasted or dropped into conversation
- Email forwarded or pulled via API
- Transcript from a call or meeting
- Screenshot shared
- Content pasted from another app
- API context pulled (Gmail, Slack, Calendar)
- Research completed during a session
- The human says "capture this" or "add this"
- Squirrel detects external content and offers to capture
- The human says "check inbox", "clear inputs", or "what's in my inbox"
- Capture is invoked with no obvious in-conversation content (triggers inbox scan — see below)
Capture is one of two operations that writes mid-session (the other is bundle drafts). Everything else waits for save.
Three Stages
Stage 0 — Detect and Classify (instant)
No processing. Just identification.
- ref_type — email, transcript, screenshot, document, message, article, research
- sensitivity — public, private, restricted (default: private)
- source — gmail, slack, web, manual, in-session
Stage 1 — Store Raw + Route to Bundle (always happens, non-negotiable)
Even if extraction fails or is skipped, the raw content is preserved.
Pre-capture check: Before proposing a destination, grep the target walnut's bundle manifests and brief.md files for the inbox filename. If found, the file is already referenced — route into that bundle's raw/ with a note "file was already cited by this bundle" rather than creating a duplicate reference elsewhere.
Routing decision: Check _kernel/now.json for an active bundle: field.
If active bundle exists — all three steps are mandatory, not optional:
- Write raw file →
{bundle}/raw/[name].[ext]with frontmatter added (type, date, source, squirrel — see type-specific templates below) - Update manifest → add entry to
context_routes:list in{bundle}/context.manifest.yamlwithpath:,description:,type:,date:(see Manifest Enrichment below) - Add inline summary → append structured summary to manifest body (## Summary, ## Key Points, ## Action Items) so the raw file rarely needs to be re-read
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 · 329 lines · 74 tokens per session scan A f3d4f2bdf966
alive:capture-context is a skill published in the GitHub repository alivecontext/alive (130 stars, last pushed 15d ago), licensed MIT. It adds 74 tokens to every session and 3,267 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 2026-08-30.
Other skills, from other repositories
fresh-start
Continue in a new chat without losing anything — writes a compact handoff to paste into a fresh conversation. Use whenever the user wants to move to a new chat or conversation, hits usage limits, says replies got slow or Claude forgets earlier details, or the conversation has grown long.
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.
brain-log
Show brain sync and evolution history.
writing-handoff
Use when an auto-compaction system reminder appears, when the user explicitly invokes /handoff or asks to "write a handoff" / "save state", or when the user signals they're near the context limit specifically ("running low on context", "almost out of context", "context is getting full"). Do NOT fire on general…
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
mnemon
Persistent graph-based memory. Recall context before responding, remember insights after. Each group has private memory; global memory is read-only.