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 NickCrew/Claude-Cortex --skill atlas-crew-tasksgit clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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/nickcrew/claude-cortex/atlas-crew-tasks)<a href="https://agentmods.dev/skills/nickcrew/claude-cortex/atlas-crew-tasks"><img src="https://agentmods.dev/badge/skills/nickcrew/claude-cortex/atlas-crew-tasks.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 | $0.00152 | $0.01343 |
| Opus 5 | $0.00076 | $0.00672 |
| Sonnet 5 | $0.00030 | $0.00269 |
| Haiku 4.5 | $0.00015 | $0.00134 |
Grade A, and why
atlas-crew-tasks 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 4d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atlas Crew Task Tracking
Work for these repos lives in GitHub Issues on Projects v2 boards, not
backlog.md. (A repo's backlog/ directory is a frozen archive of completed
pre-migration work — read-only.)
The two boards
| Board | Repos | URL |
|---|---|---|
| #8 Atlas Crew Security (shared) | Apparatus, Chimera, Crucible, Synapse, Bridge | https://github.com/orgs/atlas-crew/projects/8 |
| #9 Facet (standalone) | Facet | https://github.com/orgs/atlas-crew/projects/9 |
Both are org-owned by atlas-crew. Always pass --owner atlas-crew.
Classification model (three orthogonal axes)
Keep these separate — do not encode type or area as a label.
- Type → GitHub Issue Type (org-owned, shared by every repo):
Feature,Bug,Task,Chore(refactor/tech-debt/maintenance),Spike(time-boxed investigation). - Area → an Area single-select project field. Facet #9 only so far (Identity, Pipeline, Prep, Letters, Research, Build/Resume, Debrief, AI/Proxy, UI/Design System, Persistence, Testing/Infra, Docs, Cross-cutting). Board #8 has no Area field yet.
- Concern → labels:
accessibility,security,ux,cross-cutting,testing,documentation,playwright, plus GitHub/dependabot conventions.
Cross-repo grouping is the Initiative single-select on board #8 (e.g. "Platform Hardening", "Vuln Content") — use it for milestones that span ACS repos. Within a single repo, use native GitHub milestones.
Status differs per board:
- #9 Facet:
Backlog → Todo → In Progress → Blocked → Done. - #8 ACS:
Todo → In Progress → Done(not yet refined).
Filing a task
# 1. create the issue (type can be set at creation via REST; see gotcha below)
gh issue create --repo atlas-crew/Facet --title "..." --body "..." --label ux
# 2. add it to the board
gh project item-add 9 --owner atlas-crew --url <issue-url>
# 3. set Type (see gotcha), then set project fields (Priority/Area/Status)
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.
- 4d ago First seen · 121 lines · 152 tokens per session scan A 0fc4ef12c6dd
atlas-crew-tasks is a skill published in the GitHub repository NickCrew/Claude-Cortex (38 stars, last pushed 2mo ago), licensed MIT. It adds 152 tokens to every session and 1,343 once invoked, about $0.0008 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
team-release
Orchestrate the release team: coordinates release-manager, qa-lead, devops-engineer, and producer to execute a release from candidate to deployment.
status
Show a comprehensive project status dashboard: task queue, blocked items, session state, verification, and git status.
work-beads
Work the project's Beads task queue end-to-end - claim a bead, build in an isolated worktree, verify, review, merge, close, report. Use when the user says "/work-beads", "/work-beads 5", "work the next N beads", "work on ", "pick up some open tasks", or asks to work the backlog. Applies to every coding agent (Claude…
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.
finalize-phase
Completes feature/epic workflows after deployment with comprehensive walkthrough generation for epics (v5.0+), roadmap updates, artifact archival, documentation, and branch cleanup. Use after /ship-prod, /deploy-prod, or /build-local completes, or when user asks to finalize. (project).
workflow-detection
Provides centralized workflow type detection for all phase and deployment commands.