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-cleanupgit 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-cleanup)<a href="https://agentmods.dev/skills/alivecontext/alive/alive-cleanup"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/alive-cleanup/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-cleanup"><img src="https://agentmods.dev/badge/skills/alivecontext/alive/alive-cleanup.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 | $0.00020 | $0.00715 |
| Opus 5.5 | $0.00008 | $0.00286 |
| Sonnet 5.5 | $0.00004 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
alive-cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
System Cleanup
Scan across all walnuts for entropy. Surface issues one at a time.
Checks
1. Unsaved Sessions
grep -l "saves: 0" "$ALIVE_WORLD_ROOT/.alive/_squirrels/"*.yaml 2>/dev/null
For each: check transcript file size before dismissing. saves: 0 + stash: [] does NOT mean empty -- the stash is only written at save.
[N] unsaved sessions found.
[id] -- [date] -- [walnut] -- transcript: [size]
Review transcripts for lost work?
1. Yes, check them all
2. Show me the list first
3. Clear and move on
2. Stale Bundles
Find bundles in draft status unchanged for 30+ days:
find "$ALIVE_WORLD_ROOT" -name "context.manifest.yaml" -mtime +30 2>/dev/null
For each stale bundle:
"[bundle-name]" has been in draft for [N] days.
1. Advance it (prototype/published)
2. Archive it (set status: done)
3. Kill it (delete -- drafts are disposable)
4. Leave it
3. Stale Walnuts
Walnuts past 2x their rhythm with no recent sessions:
[walnut] -- waiting -- [N] days past weekly rhythm
1. Load it (check what's there)
2. Archive it (move to 01_Archive)
3. Update rhythm (maybe it's monthly now)
4. Leave it
4. Empty Tasks
Walnuts with stale or empty task files:
find "$ALIVE_WORLD_ROOT" -name "tasks.json" -exec python3 -c "
import json, sys
data = json.load(open(sys.argv[1]))
tasks = data.get('tasks', [])
active = [t for t in tasks if t.get('status') not in ('done', 'archived')]
if active:
print(f'{sys.argv[1]}: {len(active)} open tasks')
" {} \;
5. Legacy Structure Detection
Look for v1/v2 patterns that should be migrated:
_core/directories (v1)_kernel/_generated/directories (v2)now.mdfiles (v1)tasks.mdfiles (v1)
Found [N] walnuts with legacy structure.
1. Migrate now
2. Show me which ones
3. Skip
One at a Time
Surface issues one at a time. Don't overwhelm. Fix one, then ask if they want to continue.
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 · 107 lines · 20 tokens per session scan A 0ff68be12e44
alive-cleanup is a skill published in the GitHub repository alivecontext/alive (130 stars, last pushed 18d ago), licensed MIT. It adds 20 tokens to every session and 715 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
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.
resuming-from-handoff
Use when user invokes /handoff-resume, says "pick up where we left off", "continue from last session", "what was I working on", or starts a session with a reference to prior work that may be captured in a previous handoff file.
crit
Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.
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.
slackcli
Read, send, search, and manage Slack workspaces with the slackcli binary. Installs slackcli if missing and checks or proposes authentication first. Use whenever the user mentions Slack or pastes a slack.com link.