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 eranw2000/claude-maintenance-skills --skill project-statusgit clone --depth 1 https://github.com/eranw2000/claude-maintenance-skillsWrote 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/eranw2000/claude-maintenance-skills/project-status)<a href="https://agentmods.dev/skills/eranw2000/claude-maintenance-skills/project-status"><img src="https://agentmods.dev/badge/skills/eranw2000/claude-maintenance-skills/project-status/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/eranw2000/claude-maintenance-skills/project-status"><img src="https://agentmods.dev/badge/skills/eranw2000/claude-maintenance-skills/project-status.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 | $0.00116 | $0.02256 |
| Opus 5.5 | $0.00046 | $0.00902 |
| Sonnet 5.5 | $0.00023 | $0.00451 |
| Haiku 4.5 | $0.00012 | $0.00226 |
Grade A, and why
project-status scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project status
Cold-start orientation skill. Run when you sit down on a project after being away and want a quick read on what's live, what's in flight, what's stale, and what needs your attention before you start coding.
This is a read-only skill. No commits, no merges, no deploys, no file writes. Just inspection + synthesis.
Step 1: Detect project context
Determine which project this is. Order:
- If cwd is inside a git repo: project = repo basename.
REPO_ROOT=$(git rev-parse --show-toplevel). - If cwd is inside
~/.claude/projects/<X>/: project =<X>. No repo unless one is linked. - Otherwise: bail with "Run from a project directory (git repo or ~/.claude/projects//)."
Locate the project's CLAUDE.md (in priority order):
- Repo-root
CLAUDE.md ~/.claude/projects/<project>/CLAUDE.md~/.claude/projects/<other-naming-variant>/CLAUDE.md(e.g.Python-Project-<X>)
State the detected project + CLAUDE.md path in the first line of the report.
Step 2: Gather data (run in parallel where possible)
2a. Git state (always)
git rev-parse --abbrev-ref HEAD # current branch
git status --porcelain | wc -l # dirty file count
git log -1 --format='%h %s (%cr)' # last commit, age
git rev-list --left-right --count HEAD...main 2>/dev/null # ahead/behind main
2b. Open PRs against main (needs REPO_ROOT and an authed gh CLI)
cd "$REPO_ROOT" && gh pr list --base main --state open --json number,title,headRefName,isDraft,createdAt,mergeable 2>/dev/null
For each PR, compute age in days. Flag PRs older than 14 days as stale.
The cd "$REPO_ROOT" is load-bearing. This skill is often launched from a project
data directory that sits inside a different git repository, so a bare gh resolves to
THAT repository and returns [] no matter what the project has open. It is a truthful
answer about the wrong repo, which is the worst kind. gh -R <owner>/<repo> is equally
fine. When step 1 found no REPO_ROOT, skip this section and report it as skipped,
never as zero: an empty result here is a false negative, not a clean bill.
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.
- 5d ago Changed d96d010b9c04
- 1mo ago Changed · +2 tokens per session e6384c328e4a
- 2mo ago First seen · 156 lines · 114 tokens per session scan A 1b492e914307
project-status is a skill published in the GitHub repository eranw2000/claude-maintenance-skills (8 stars, last pushed 4d ago), licensed MIT. It adds 116 tokens to every session and 2,256 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
project-status compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| project-statuseranw2000/claude-maintenance-skills | Skill | 8 | 4d ago | MIT | A | 116 | Claude Code |
| agents-v2-pylingxling/awesome-skills-cn | Skill | 329 | 1mo ago | MIT | A | 39 | Claude Code |
| analytics-productlingxling/awesome-skills-cn | Skill | 329 | 1mo ago | MIT | A | 35 | Claude Code |
| api-security-best-practiceslingxling/awesome-skills-cn | Skill | 329 | 1mo ago | MIT | A | 29 | Claude Code |
| antigravity-workflowslingxling/awesome-skills-cn | Skill | 329 | 1mo ago | MIT | A | 41 | Claude Code |
| oci-services-expertfrankxai/claude-skills-library | Skill | 47 | yesterday | MIT | A | 43 | Claude Code |
| v-swarmfrankxai/claude-skills-library | Skill | 47 | yesterday | MIT | A | 141 | Claude Code |