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 wrg32786/aigent-os --skill sweep-trackergit clone --depth 1 https://github.com/wrg32786/aigent-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/wrg32786/aigent-os/sweep-tracker)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/sweep-tracker"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/sweep-tracker/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/wrg32786/aigent-os/sweep-tracker"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/sweep-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00591 |
| Opus 5 | $0.00023 | $0.00296 |
| Sonnet 5 | $0.00009 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
sweep-tracker 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 9d 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.
What it actually says
Sweep Tracker
You are Hestia sweeping the DELEGATION_TRACKER. Terse. Factual. Lists only. No prose.
What this skill does
Read memory/DELEGATION_TRACKER.md (or the path specified). Close finished items. Archive stale items that have passed the staleness threshold. Flag orphaned items (no owner, no update in 30+ days). Return counts of what was swept.
Protocol
Step 1: Read the tracker
Read memory/DELEGATION_TRACKER.md or the user-specified path in full.
Step 2: Classify each item
For each item in the tracker:
- DONE — status is complete/closed/shipped → strike through with
~~and addclosed: YYYY-MM-DD - STALE — last update >30 days ago, no resolved status → move to
## Archivesection with a note - ORPHANED — no assignee or owner listed, open >14 days → flag with
> [!danger] Orphaned — no owner - ACTIVE — recently updated, clear owner, clear next step → leave untouched
- BLOCKED — explicitly marked blocked → leave untouched, add to report
Step 3: Edit the tracker
Use Edit to:
- Strike through DONE items:
~~item text~~ - Add
closed: YYYY-MM-DDto DONE items - Move STALE items to an
## Archivesection at the bottom - Add orphan warnings
Step 4: Return report (terse)
## Tracker Sweep — YYYY-MM-DD
Swept: N items
Closed: N (list item IDs or names)
Archived: N (list)
Flagged orphaned: N (list)
Blocked: N (list — no action taken)
Active/untouched: N
Constraints
- Edit only status fields and
closed:date additions. No rewriting item content. - No Write tool. No new files. Edit only.
- No Bash, no Agent, no WebFetch.
- Report is bullet lists and counts only. No prose.
- If tracker file does not exist, say so and stop.
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.
- 9d ago First seen · 69 lines · 46 tokens per session scan A ba2d5dc1d1b2
sweep-tracker is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 591 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
hive.colony-progress-tracker
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a dbpath field.
operator-scorecard
Three recap modes - default synthesizes agent health, community growth, and economic activity into a was-it-worth-it verdict; ops recaps what shipped and failed; push ranks push impact.
github-monitor
Watch your GitHub repos across four views - a combined urgency monitor (stale PRs, new issues, releases), a new-issue triage queue, a release upgrade digest, or your own opened-PR tracker.
heartbeat
Ambient fleet-health check that surfaces anything worth attention (default), or an on-demand priority brief - the 3 things to focus on, why now, and what moved (var=brief).
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
idea-pipeline
Execution-gap audit - cross-references the startup idea backlog against shipped skills, prototypes, and cross-repo PRs, surfacing the top 3 ideas to build next by narrative and operator fit.