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 Abilityai/abilities --skill project-stewardgit clone --depth 1 https://github.com/Abilityai/abilitiesWrote 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/abilityai/abilities/project-steward)<a href="https://agentmods.dev/skills/abilityai/abilities/project-steward"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/project-steward/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/abilityai/abilities/project-steward"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/project-steward.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 | $0.00168 | $0.11402 |
| Opus 5.5 | $0.00067 | $0.04561 |
| Sonnet 5.5 | $0.00034 | $0.02280 |
| Haiku 4.5 | $0.00017 | $0.01140 |
Grade A, and why
project-steward 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 6d 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 -sL "https://github.com/cli/cli/releases/download/v2.63.2/gh_2.63.2_linux_amd64.tar.gz" | tar xz -C /tmp/ How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Steward
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.project-steward v1.9.1 — recent: arguments no longer break the config resolver. Then proceed.
Purpose
Keep every managed project moving without the operator having to push it. Each run:
- Reconcile outstanding dispatches (read agent replies, post relay comments, verify done claims)
- Review every open project epic: verify pending-verification tasks, dispatch next work, escalate stalls
- Sweep open loops (Invariant 7): age every
waiting-on:*task, draft the operator's nudges, keep unanswered asks alive - Run the quarantine pass: auto-stub unregistered workspace folders
- Write the digest (material runs only), opening with what the operator now knows and what is waiting on them
This skill never asks a human anything mid-run. Anything ambiguous gets $L_NEEDS_OPERATOR and moves on. It is the sole writer of steward update comments on GitHub issues.
It does close loops, in both directions (standard §14). Nothing it touched ends in silence: work the operator initiated is reported back to the operator, an unanswered ask is re-surfaced with its age rather than dropped, and every loop parked on a third party is aged in the digest with a ready-to-send nudge. It drafts those nudges; it never sends them — contacting a client, vendor, or outside colleague is the human's act, always.
Deliberate non-composition: this skill dispatches only to owners explicitly named by agent:* labels — no routing judgment. The interactive disambiguation that /orchestrate provides would hang an unattended run.
Trinity is optional. When Trinity MCP is unavailable, the skill runs in triage-only mode: all registry operations continue; dispatch is skipped and noted in the digest. Nothing is lost.
On Trinity with Projects enabled the platform holds the project record (standard §17): the same steps then run against it — see Platform projects below. Off Trinity nothing changes.
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.
- 6d ago Changed · +1 lines bd9ef34fb78b
- 7d ago Changed · +42 lines f5a42057d113
- 9d ago Changed · +23 lines · +36 tokens per session 551cfd2b52ad
- 11d ago Changed · +46 lines · +28 tokens per session 30ad8f0ef29e
- 29d ago Changed · +4 lines beb2bb3df80a
- 1mo ago First seen · 266 lines · 104 tokens per session scan A 75eb5f072b3f
project-steward is a skill published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 168 tokens to every session and 11,402 once invoked, about $0.0007 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 2026-09-07.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…