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-reconcilegit 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-reconcile)<a href="https://agentmods.dev/skills/abilityai/abilities/project-reconcile"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/project-reconcile/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-reconcile"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/project-reconcile.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 | $0.00110 | $0.04788 |
| Opus 5.5 | $0.00044 | $0.01915 |
| Sonnet 5.5 | $0.00022 | $0.00958 |
| Haiku 4.5 | $0.00011 | $0.00479 |
Grade A, and why
project-reconcile 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 -sf "https://tasks.googleapis.com/tasks/v1/users/@me/lists" \ How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Reconcile
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — e.g.
project-reconcile v1.4.1 — recent: arguments no longer break the config resolver. Then proceed.
Purpose
Sync projection surfaces (personal task views, team tools) against the GitHub Issues registry. The registry is write-authoritative; projections are read-only displays with one-directional gesture processing.
Key rules (Invariant 5):
- Projections display state; they do not own it.
[#NN]prefix in the projection item title is the join key — unkeyed items cannot be synced.- Gestures are typed by reversibility: check (completion endorsement), date-push (defer signal, no registry write), delete (soft-skip proposal, registry item survives).
- Absence is never authoritative.
Adapters
This skill ships with the Google Tasks adapter v1. Other adapters (Fibery, Notion, Linear, etc.) follow the adapter contract in PROJECT_STANDARD.md §11 and are per-deployment extensions — copy this skill, implement the three adapter methods, and register your adapter in the dispatch block below.
Platform mode (Trinity Projects — standard §17)
On a Trinity instance with Projects enabled, the platform holds the project record (ruling R38) and this skill works against it. Without Trinity, or where Projects is not enabled, nothing in this section applies and the skill runs exactly as written below.
Check once per run, after the standard is resolved. PLATFORM=$(cfg platform auto). Platform mode is off when that is off, or when this session has no mcp__trinity__list_projects tool. Otherwise call mcp__trinity__list_projects:
enabled: true→ on; itsprojectsare the platform projects this agent works on.enabled: false→ off (an install without Projects, an unlicensed one, or a local session on a person's key). Say nothing; carry on in folder + GitHub mode.enabled: falsewith amessageabout internal conversations, or any project tool refusing withcode: external_audienceorturn_unknown→ someone outside the company is in this conversation, or the platform cannot identify the turn: platform mode is off for the run, and no project detail read from the platform is repeated here.
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 f50e893761cd
- 7d ago Changed · +20 lines 176b33437955
- 9d ago Changed · +18 lines · +15 tokens per session d9faa9abe53e
- 11d ago Changed · +4 lines · +14 tokens per session 6b51784dc21a
- 1mo ago First seen · 244 lines · 81 tokens per session scan A dc89e646257d
project-reconcile is a skill published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 110 tokens to every session and 4,788 once invoked, about $0.0004 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…