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 alive-savegit 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/alive-save)<a href="https://agentmods.dev/skills/alivecontext/alive/alive-save"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/alive-save/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/alive-save"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/alive-save.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 | $0.00021 | $0.00775 |
| Opus 5.5 | $0.00008 | $0.00310 |
| Sonnet 5.5 | $0.00004 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
alive-save 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save
Route the stash, write the log, update the bundle, trigger projection.
Pre-Save
- Ask: "Anything else before I save?"
- Scan back through conversation for missed stash items
- Present stash grouped by type:
Stash (N items):
Decisions:
1. [decision] -> [walnut]
2. [decision] -> [walnut]
Tasks:
3. [task] -> [walnut]
Notes:
4. [note] -> [walnut]
5. [note] -> [[person]]
Confirm, edit, or drop items?
Write Log Entry
Prepend to _kernel/log.md after frontmatter. Use terminal:
# Read existing log, prepend new entry after frontmatter
Entry format:
## YYYY-MM-DDTHH:MM:SS -- squirrel:[session_id]
**Type:** [feature/decision/research/strategy/etc]
[Narrative paragraph -- what happened, why, what it means]
### Decisions
- [decision with rationale]
### Artifacts
- [files created/modified]
signed: squirrel:[session_id]
Update Active Bundle
Write to the active bundle's context.manifest.yaml:
- Update
context:field with current state - Update
status:if changed
Route Tasks
Confirmed task-shaped stash items are promoted in a single batch via alive tasks promote after the squirrel YAML stash is written. The CLI walks each type: task stash item, writes the task row, and stamps promotion_state / task_id markers back onto the squirrel file under a single flock for crash safety.
"$ALIVE_PLUGIN_ROOT/bin/alive" tasks promote \
--squirrel "[session_id]" \
--walnut "[path]"
Python fallback if bin/alive is missing:
"${ALIVE_PYTHON:-python3}" "$ALIVE_PLUGIN_ROOT/scripts/cli.py" tasks promote \
--squirrel "[session_id]" --walnut "[path]"
For non-promotion edits on existing tasks (mark done, change priority), use tasks.py directly:
python3 "$ALIVE_PLUGIN_ROOT/scripts/tasks.py" done --walnut "[path]" --id "[task_id]"
Never read or write tasks.json directly. Fail-loud if the CLI binary is missing on both paths — do not fall back to per-item adds from the agent.
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 · 130 lines · 21 tokens per session scan A d7216d5bf61b
alive-save is a skill published in the GitHub repository alivecontext/alive (130 stars, last pushed 17d ago), licensed MIT. It adds 21 tokens to every session and 775 once invoked, about $0.0001 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
doc-digest
Turn a long document, PDF, transcript, spreadsheet or log into a compact working digest the conversation can continue from. Use when the user shares or pastes something long (several pages or more) and wants to discuss, analyze, compare or use it over more than one message, or asks to summarize a document so they can…
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.
project-context
Turn background the user keeps re-explaining or re-pasting into reusable instructions, so new chats start with it for free. Use when the user repeats the same context, rules, style guide, persona or reference text across messages or chats, says they are tired of explaining the same thing, or asks how to set up a…
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…