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 agentmods add skills/alivecontext/alive/alive-savenpx 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.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 | $0.00021 | $0.00775 |
| Opus 5 | $0.00010 | $0.00387 |
| Sonnet 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 4d 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.
- 4d ago First seen · 130 lines · 21 tokens per session scan A d7216d5bf61b
alive-save is a skill published in the GitHub repository alivecontext/alive (127 stars, last pushed 8d ago), licensed MIT. It adds 21 tokens to every session and 775 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
cco-overhead
Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage.
handoff
Create a session briefing for the next session — auto-loaded, then archived. Use when the user is wrapping up a session, says "save this for next time", "hand off", "brief the next session", or wants to ensure continuity before stopping work.
forget
Remove entries from remembered items. Use when the user wants to delete, remove, or clear a previously remembered item, or says "forget this", "remove that memory", or "clear my preferences".
recall
Inject filtered context from previous sessions. Use when the user says "recall", "what happened last session", "what did we work on", "inject previous context", or when you need context from a prior session to continue work. Also useful mid-session when the user references prior work you don't have context for.
remember
Save something to memory for future sessions. Use when the user says "remember this", "save for later", "don't forget", or wants to persist any preference, fact, lesson, or note across sessions.
status
Check plugin health and diagnose issues. Use when the user asks about mneme health, memory status, plugin errors, wants to troubleshoot memory issues, or sees error warnings at session start.