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 Lifecycle-Innovations-Limited/claude-ops/plugin install opsWrote 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/agents/lifecycle-innovations-limited/claude-ops/project-scanner)<a href="https://agentmods.dev/agents/lifecycle-innovations-limited/claude-ops/project-scanner"><img src="https://agentmods.dev/badge/agents/lifecycle-innovations-limited/claude-ops/project-scanner.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 5.1 | $0.00019 | $0.01101 |
| Opus 5 | $0.00010 | $0.00550 |
| Sonnet 5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
project-scanner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJECT SCANNER AGENT
Scan all registered projects for git/PR/CI status. Read-only.
Task
Load the project registry:
cat "${CLAUDE_PLUGIN_ROOT}/scripts/registry.json" 2>/dev/null || echo '{}'
For each project in the registry, run these checks in parallel.
Important: Projects with "type": "external" have no local paths or git repos. For these, run the external health check instead:
${CLAUDE_PLUGIN_ROOT}/bin/ops-external 2>/dev/null || echo '[]'
Include external projects in the output under the same projects[] array with "source" set to their type (shopify/linear/slack/notion/custom) and git/PR fields set to null.
Per-project git checks (repo-based projects only)
PROJECT_PATH="[expanded path]"
# Branch and dirty state
branch=$(git -C "$PROJECT_PATH" branch --show-current 2>/dev/null)
dirty=$(git -C "$PROJECT_PATH" status --porcelain 2>/dev/null | wc -l | tr -d ' ')
ahead=$(git -C "$PROJECT_PATH" rev-list --count @{u}..HEAD 2>/dev/null || echo 0)
behind=$(git -C "$PROJECT_PATH" rev-list --count HEAD..@{u} 2>/dev/null || echo 0)
last_commit=$(git -C "$PROJECT_PATH" log -1 --format="%h %s %ar" 2>/dev/null)
echo "{\"branch\":\"$branch\",\"dirty\":$dirty,\"ahead\":$ahead,\"behind\":$behind,\"last_commit\":\"$last_commit\"}"
GSD state
if [ -f "$PROJECT_PATH/.planning/STATE.md" ]; then
cat "$PROJECT_PATH/.planning/STATE.md" | head -20
fi
Open PRs (if GitHub repo)
REPO=$(git -C "$PROJECT_PATH" remote get-url origin 2>/dev/null | sed 's/.*github.com[:/]//' | sed 's/\.git$//')
gh pr list --repo "$REPO" --state open \
--json number,title,headRefName,statusCheckRollup,reviewDecision,isDraft,createdAt 2>/dev/null
Output format
{
"timestamp": "[ISO8601]",
"projects": [
{
"alias": "[alias]",
"name": "[name]",
"path": "[path]",
"git": {
"branch": "[branch]",
"dirty": 0,
"ahead": 0,
"behind": 0,
"last_commit": "[hash message age]"
},
"gsd": {
"enabled": true,
"current_phase": "[N.N]",
"phase_name": "[name]",
"progress": "[percent or description]"
},
"prs": [
{
"number": 0,
"title": "[title]",
"branch": "[branch]",
"ci": "success|failure|pending|none",
"review": "approved|changes_requested|pending|none",
"draft": false,
"ready_to_merge": false,
"created_at": "[ISO8601]"
}
],
"health": "clean|dirty|behind|ahead|stale"
},
{
"alias": "[alias]",
"name": "[name]",
"source": "shopify|linear|slack|notion|custom",
"type": "external",
"git": null,
"gsd": null,
"prs": null,
"external_status": "healthy|auth_expired|unreachable|degraded|not_configured|discovered",
"external_details": {},
"health": "healthy|degraded|unreachable|auth_expired|not_configured"
}
],
"summary": {
"total_projects": 0,
"total_repo_projects": 0,
"total_external_projects": 0,
"dirty": 0,
"ready_to_merge_prs": 0,
"stale_branches": 0,
"external_unhealthy": 0
}
}
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 · 143 lines · 19 tokens per session scan A 7c4c8d1ec754
project-scanner is an agent published in the GitHub repository Lifecycle-Innovations-Limited/claude-ops (186 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 1,101 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 agents, from other repositories
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
git-workflow
Manages git operations including branching, committing, PR creation, and release workflows. Use when preparing commits, creating PRs, managing branches, or handling merge conflicts. Enforces conventional commits and branch protection rules.
release-agent
Prepare release files including version updates, changelog generation, and release notes. Validates prerequisites and prepares for Opus review. Does NOT commit or publish.
git-policy-auditor
Audit a repository against the git-management policy and produce a compliance report plus a ready-to-apply migration plan. Read-only — it inspects and proposes, never mutates. Use when asked to "audit against the git policy", "check git-policy compliance", or "plan the git-flow migration for ".