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 davistroy/claude-marketplace/plugin install personal-pluginWrote 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/davistroy/claude-marketplace/archive-project)<a href="https://agentmods.dev/skills/davistroy/claude-marketplace/archive-project"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/archive-project/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/davistroy/claude-marketplace/archive-project"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/archive-project.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 | $0.00078 | $0.02851 |
| Opus 5 | $0.00039 | $0.01425 |
| Sonnet 5 | $0.00016 | $0.00570 |
| Haiku 4.5 | $0.00008 | $0.00285 |
Grade A, and why
archive-project 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 7d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archive Project
You are retiring a project: recording why it ended and what was learned, tagging the final state, optionally archiving the remote, and relocating the directory out of active ~/dev/ space into a labeled archive — while keeping a single running index (~/dev/PORTFOLIO.md) of what's active, paused, and archived.
This skill is destructive-adjacent: it moves a directory on disk and can archive a remote repo (which, on GitHub, makes it read-only). It never deletes git history — everything is preserved via commit, tag, and mv — but the actions are not casually reversible mid-session. Confirm before acting.
Input
Arguments: $ARGUMENTS
Required:
<repo-path>— path to the project directory to archive (e.g.~/dev/personal/old-experiment). If omitted, ask the user.
Optional (ask for these in Phase 0 if not supplied):
--reason "<text>"— why the project is being archived--lesson "<text>"— the "what I learned" / "what worked" line--superseded-by "<name-or-path>"— the project that replaces this one, if any--archive-remote— if the remote is GitHub and active, archive it after pushing (skipped for local-only or already-archived remotes; irrelevant for non-GitHub remotes)
Destructive Action Warning
Before touching anything:
- Confirm the exact target directory with the user (typos here move or archive the wrong project)
- Never run this against a path that looks like an active dependency of other projects without asking
- Archiving a GitHub remote makes it read-only — pushes will fail afterward. Only do this if the user confirmed archive-remote intent
- If
git statusin the target shows uncommitted changes unrelated to the archival header, ask before proceeding — don't silently fold unrelated work into the archival commit
Procedure
Phase 0: Confirm Target
- Resolve
<repo-path>to an absolute path. If it doesn't exist or isn't a git repo (no.git), stop and report the error. - Gather facts and show them to the user before doing anything else:
REPO="<resolved-absolute-path>" cd "$REPO" git remote -v git log -1 --format='%h %ad %s' --date=short git status -s - Display a confirmation summary:
Archive target: <REPO> Remote: <url, or "none (local-only)"> Last commit: <date> <hash> <subject> Uncommitted: <"clean" | list of changes> This will: write an archival header into README.md, tag and commit, [push + offer to archive the remote | skip remote steps — no remote], then move the directory to ~/dev/archive/<org>/<name>/. Proceed? (y/n) - If the user hasn't already supplied
--reason/--lesson/--superseded-by, ask for them now:- Reason for archiving (required)
- What worked / what you learned (required — one or two sentences)
- Superseded by, if anything (optional)
- Do not proceed past this point without explicit confirmation.
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.
- 7d ago First seen · 227 lines · 78 tokens per session scan A 96ecdffb472f
archive-project is a skill published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 2,851 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
gsd-complete-milestone
Archive completed milestone and prepare for next version.
operating-github-cli
Default GitHub skill for the action agent. Use githubcli for any GitHub request — create/list/view/close issues and PRs, assign, labels, repos, releases, checks, github.com/owner/repo URLs, or gh api. Prefer over shellrun/!gh. Run these with githubcli in the current agent turn.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
testdino-releases
Use when the user wants to browse, inspect, create, or update releases/milestones in a TestDino project. Covers listreleases, getrelease, createrelease, and updaterelease. Accepts counter-style IDs like MS-12.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.