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 dailyaiagents-cpu/dailyai-os --skill stale-gate-janitorgit clone --depth 1 https://github.com/dailyaiagents-cpu/dailyai-osWrote 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/dailyaiagents-cpu/dailyai-os/stale-gate-janitor)<a href="https://agentmods.dev/skills/dailyaiagents-cpu/dailyai-os/stale-gate-janitor"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/stale-gate-janitor/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/dailyaiagents-cpu/dailyai-os/stale-gate-janitor"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/stale-gate-janitor.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 | $0.00041 | $0.01442 |
| Opus 5 | $0.00020 | $0.00721 |
| Sonnet 5 | $0.00008 | $0.00288 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
stale-gate-janitor 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 12d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(args, timeout=10, check=False) How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stale-gate-janitor
Why this exists
Active approval-gates dir accumulates resolved + expired entries that audit reads (hermes-daily-audit) keep tripping on. Today's session (2026-04-29) caught 3 stale Apr-28 gates Cooper had to mentally filter every morning. This skill removes that toll.
Inputs
{
"dry_run": false,
"test_telegram_chat_id": null
}
dry_run=true walks + classifies but doesn't write or Telegram.
test_telegram_chat_id (env var TELEGRAM_TEST_CHAT_ID) — if set, sends summary to that chat instead of Cooper's. Used by self-test to avoid pinging Cooper during ops verification.
Procedure
Step 1 — Walk + classify
import json, datetime, pathlib, shutil, os, subprocess
home = pathlib.Path.home()
repo = home / "Dev/daily-ai-agent-os"
gates_dir = repo / "data/approval-gates"
archive_root = gates_dir / "archive"
now = datetime.datetime.now(datetime.timezone.utc)
if not gates_dir.exists():
print("[stale-gate-janitor] no approval-gates dir; nothing to do")
raise SystemExit(0)
ARCHIVE_AGE_S = 7 * 86400
expired_now = []
archived = []
errors = []
# Pass 1 — expire stale-pending gates
for p in gates_dir.glob("*.json"):
if p.parent != gates_dir: # skip archive subdir
continue
try:
g = json.loads(p.read_text())
except Exception as e:
errors.append({"file": str(p), "err": f"parse: {e}"})
continue
if g.get("status") in (None, "pending", "open"):
ex_iso = g.get("expires_at", "")
try:
ex_dt = datetime.datetime.fromisoformat(ex_iso.replace("Z", "+00:00")) if ex_iso else None
except Exception:
ex_dt = None
if ex_dt and ex_dt < now:
g["status"] = "expired"
g["expired_at"] = now.isoformat()
g["expired_by"] = "stale-gate-janitor"
p.write_text(json.dumps(g, indent=2))
expired_now.append(g.get("id", p.stem))
# Pass 2 — archive >7d files
for p in list(gates_dir.glob("*.json")):
if p.parent != gates_dir:
continue
age_s = now.timestamp() - p.stat().st_mtime
if age_s <= ARCHIVE_AGE_S:
continue
try:
g = json.loads(p.read_text())
ts = g.get("created_at") or g.get("expires_at") or now.isoformat()
ym = ts[:7] # YYYY-MM
except Exception:
ym = now.strftime("%Y-%m")
bucket = archive_root / ym
bucket.mkdir(parents=True, exist_ok=True)
target = bucket / p.name
shutil.move(str(p), str(target))
archived.append(p.stem)
print(f"[stale-gate-janitor] expired={len(expired_now)} archived={len(archived)} errors={len(errors)}")
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 146 lines · 41 tokens per session scan A 855428eb9967
stale-gate-janitor is a skill published in the GitHub repository dailyaiagents-cpu/dailyai-os (0 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,442 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.