Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add choiyounggi/groundwork/plugin install file-lifecycleWrote 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/choiyounggi/groundwork/archive)<a href="https://agentmods.dev/skills/choiyounggi/groundwork/archive"><img src="https://agentmods.dev/badge/skills/choiyounggi/groundwork/archive/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/choiyounggi/groundwork/archive"><img src="https://agentmods.dev/badge/skills/choiyounggi/groundwork/archive.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00115 | $0.00667 |
| Opus 5.5 | $0.00046 | $0.00267 |
| Sonnet 5.5 | $0.00023 | $0.00133 |
| Haiku 4.5 | $0.00012 | $0.00067 |
Grade A, and why
archive 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 2d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
file-lifecycle: archive
Session scratch files live in $CLAUDE_SESSION_TMP and are deleted after the grace
period once the session ends. Anything a later session should see goes to the
archive. The tool is ${CLAUDE_PLUGIN_ROOT}/scripts/archive.py; the archive root is
archive_root in ~/.claude/groundwork/file-lifecycle.json (default ~/claude-archive).
1. Look before you create
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/archive.py" find <term>...
Or read <archive_root>/INDEX.md. If a file with the same purpose exists, use or
update that one instead of making a second copy.
2. Archive
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/archive.py" add <path>... \
--cat <reports|plans|data|backups|notes|scripts> \
--topic "what it is" --why "why it exists and when to reuse it" \
[--slug short-name] [--ticket KEY-1] [--review YYYY-MM-DD] [--copy]
- Write
--whyso a reader can decide from that line alone whether to open the file: where it came from, and the condition under which it is reused. - The file is moved (use
--copyto keep the source). Symlinks are never moved. - The tool names the file
<category>/<YYYY-MM-DD>_<slug>and refuses content that is already archived.
3. When the secret scan refuses
The scan fails closed. Do not work around it.
- A pattern hit: remove the value from the file, or leave the file out. Pass
--accept-hit <path>only after you read the hit and it is an example or a placeholder — never for a real value. - "cannot be scanned" (too large, binary, unreadable archive): look at the content,
then pass
--allow-unscanned. Pattern hits still block. - A file that holds a secret does not belong in the archive at all.
4. Maintenance
archive.py check— index/file drift and overdue--reviewdates (exit 1 on problems).archive.py remove <path> --yes— only when the user asks; the archive never deletes on its own.python3 "${CLAUDE_PLUGIN_ROOT}/scripts/tmp_lifecycle.py" status— what the next sweep would delete, without deleting it.
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.
- 2d ago First seen · 54 lines · 115 tokens per session scan A e5017a1bb241
archive is a skill published in the GitHub repository choiyounggi/groundwork (3 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 667 once invoked, about $0.0005 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 2026-10-22.
Other skills, from other repositories
high-output-management
Manage for output using Grove's "High Output Management": a manager's output is their organization's output, raised by high-leverage activities. Use when the user mentions "high output management", "managerial leverage", "one-on-ones", "1:1 agenda", "OKRs", "performance review", "task-relevant maturity", "delegation"…
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…
drive-motivation
Design motivation systems using Autonomy, Mastery, and Purpose (AMP) for products and teams. Use when the user mentions "intrinsic motivation", "gamification isnt working", "rewards arent working", "autonomy", "mastery", "purpose-driven", "my team is disengaged", or "how do I motivate people". Also trigger when…
new
Start a new session — save summary to memory, then mark as reset so next message gets a fresh greeting. OpenClaw-compatible. Triggers on /new, /reset, /agent:new, "nueva sesión", "new session", "reset".
alive-morning
Morning briefing -- read all walnut states, surface priorities, inbox count, stale walnuts, people nudges.
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.