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 load-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/load-context)<a href="https://agentmods.dev/skills/alivecontext/alive/load-context"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/load-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/load-context"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/load-context.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 | $0.00081 | $0.02815 |
| Opus 5.5 | $0.00032 | $0.01126 |
| Sonnet 5.5 | $0.00016 | $0.00563 |
| Haiku 4.5 | $0.00008 | $0.00281 |
Grade A, and why
alive:load-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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load
Load a walnut. See where things are. Work.
Default: single-walnut focus. But people involved are loaded automatically (frontmatter only) — you can't work on a venture without knowing who's in it.
If No Walnut Named
Show available walnuts as a numbered list grouped by domain:
╭─ 🐿️ pick a walnut
│
│ Life
│ 1. identity active Mars visa application
│ 2. health quiet Sleep study results
│
│ Ventures
│ 3. nova-station active Orbital test window
│ 4. paper-lantern quiet Menu redesign
│
│ Experiments
│ 5. midnight-frequency active Episode 12 edit
│ 6. glass-cathedral waiting Decide: gallery or festival
│
│ ▸ Number to load, or name one.
╰─
Tier 1 — Brief Pack (3 files) + claim the session
Read these three files. That's it — everything you need to orient.
_kernel/key.md— full file (identity, people, links, rhythm)_kernel/now.json— full file (phase, bundle statuses with task summaries, recent sessions, nested walnut state, blockers, context paragraph)_kernel/insights.md— frontmatter only (what domain knowledge sections exist)- Claim this session for the walnut — Edit
.alive/_squirrels/{your-session-id}.yamland change thewalnut:field fromnullto the walnut's directory basename (e.g.walnut: berties,walnut: alive-os). Your session ID is in the SessionStart injection at the top of context (Session ID: ...); the squirrel YAML lives under the world's.alive/_squirrels/directory using the full UUID as the filename. This step is mandatory, not optional. Cross-session hooks (alive-context-watch.sh, the statusline,project.py's recent-sessions aggregator) all readwalnut:from this YAML to know which walnut you're on. If you skip this, parallel-session change detection silently no-ops, the statusline shows the wrong context, and projections under-count your activity. Use a single Edit withold_string: "walnut: null"andnew_string: "walnut: {name}". If the YAML already has a different walnut name (rare — cross-walnut session), leave it and surface the conflict to the human.
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 · 265 lines · 81 tokens per session scan A c173274084db
alive:load-context is a skill published in the GitHub repository alivecontext/alive (130 stars, last pushed 15d ago), licensed MIT. It adds 81 tokens to every session and 2,815 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.