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 crussella0129/Animus_Sprint_Loops --skill sprint-loopsgit clone --depth 1 https://github.com/crussella0129/Animus_Sprint_LoopsWrote 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/crussella0129/animus_sprint_loops/sprint-loops)<a href="https://agentmods.dev/skills/crussella0129/animus_sprint_loops/sprint-loops"><img src="https://agentmods.dev/badge/skills/crussella0129/animus_sprint_loops/sprint-loops/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/crussella0129/animus_sprint_loops/sprint-loops"><img src="https://agentmods.dev/badge/skills/crussella0129/animus_sprint_loops/sprint-loops.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 | $0.00058 | $0.00627 |
| Opus 5 | $0.00029 | $0.00313 |
| Sonnet 5 | $0.00012 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
sprint-loops 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 11d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Loops for Codex
This file is the Codex adapter and router. The selected phase file owns the phase contract; the Project Book owns durable project meaning and state.
Activation
Honor the frontmatter boundary. A Book marker may confirm a direct resume request, but filesystem or documentation presence is never an activation signal by itself.
Resolve roots
<skill-root>is the directory containing this loadedSKILL.md. Resolve it from the skill path Codex supplied, and quote it in every command.<project-root>is the repository or workspace root for the target project. If Codex started in a nested Git directory, use the Git top level. For a non-Git project, use the active workspace root. Do not treat<skill-root>as the project.
Resolve both once. If multiple target projects make <project-root> ambiguous,
ask before writing.
Route
From <project-root>, run:
bash "<skill-root>/scripts/current-phase.sh"
Load only the matching phase contract:
uninitializedorready-for-next-sprint→phases/01-init-sprint.mdresearch→phases/02-research-phase.mdplan→phases/03-plan-phase.mdbuild→phases/04-build-phase.mdtest→phases/05-test-phase.mdloop→phases/06-loop-phase.md
Read phases/00-overview.md only when the Book contract or a layout diagnostic
needs interpretation. A legacy/conflict diagnostic must be resolved through
the overview and migration helper; never create a second writable state tree.
After satisfying a phase's Exit evidence, re-run the router from
<project-root>. Stop at the boundary the user requested.
Authority and collaboration
Local work remains bounded by the user's request, the active phase, and the Book's intent authority. Never change Codex sandbox, approval, or permission settings to make a phase proceed; surface an unavailable capability instead.
Push, merge, release, force-push, delete, and material scope expansion require an explicit request or a declared preauthorized-remote profile. The remote profile is declared per schemas/remote-profile.md and drives the one-PR/MR-per-sprint work -> base checkpoint (human-approve by default); the substrate gate scripts/check-substrate.sh establishes and verifies it, and the skill creates no per-sprint branch.
What ships with it
55 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.
- AGENTS.md.fragment 344 B
- phases/00-overview.md 2.5 KB
- phases/01-init-sprint.md 5.6 KB
- phases/02-research-phase.md 2.4 KB
- phases/03-plan-phase.md 2.5 KB
- phases/04-build-phase.md 3.4 KB
- phases/05-test-phase.md 3.0 KB
- phases/06-loop-phase.md 5.2 KB
- prompts/plan-critic.md 2.7 KB
- prompts/test-critic.md 2.9 KB
- schemas/agent-tasks.md 1.1 KB
- schemas/build-plan.md 1.9 KB
- schemas/completed-tasks.md 1.2 KB
- schemas/failure-report.md 1.2 KB
- schemas/intent.md 3.1 KB
- schemas/remote-profile.md 2.8 KB
- schemas/research-report.md 1.7 KB
- schemas/sprint-meta.md 2.0 KB
- schemas/test-plan.md 1.3 KB
- schemas/test-report.md 1.8 KB
- scripts/abort-sprint.sh 3.4 KB runs code
- scripts/book-paths.sh 7.7 KB runs code
- scripts/book-routing.test.sh 7.9 KB runs code
- scripts/bundle-version.sh 608 B runs code
- scripts/check-book.sh 4.3 KB runs code
- scripts/check-book.test.sh 4.3 KB runs code
- scripts/check-substrate.sh 4.3 KB runs code
- scripts/check-substrate.test.sh 7.7 KB runs code
- scripts/check-tracked.sh 1.9 KB runs code
- scripts/check-tracked.test.sh 4.3 KB runs code
- scripts/close-sprint.sh 5.9 KB runs code
- scripts/commit-task.sh 3.5 KB runs code
- scripts/critic-contract.sh 1.6 KB runs code
- scripts/current-phase.sh 1.4 KB runs code
- scripts/current-sprint.sh 643 B runs code
- scripts/deploy-substrate.sh 17 KB runs code
- scripts/deploy-substrate.test.sh 31 KB runs code
- scripts/detect-languages.sh 2.2 KB runs code
- scripts/detect-languages.test.sh 3.4 KB runs code
- scripts/finalize-plan.sh 7.2 KB runs code
- scripts/init-sprint.sh 5.2 KB runs code
- scripts/migrate-to-book.sh 28 KB runs code
- scripts/migrate-to-book.test.sh 17 KB runs code
- scripts/remote-adapter.sh 7.3 KB runs code
- scripts/remote-adapter.test.sh 13 KB runs code
- scripts/remote-profile.sh 2.7 KB runs code
- scripts/remote-profile.test.sh 5.8 KB runs code
- scripts/research-budget.sh 1007 B runs code
- scripts/runtime-helpers.test.sh 29 KB runs code
- scripts/scaffold-ci.sh 7.9 KB runs code
- scripts/scaffold-ci.test.sh 8.5 KB runs code
- scripts/selftest.sh 398 B runs code
- scripts/sync-work-branch.sh 2.0 KB runs code
- scripts/sync-work-branch.test.sh 2.4 KB runs code
- scripts/update-confidence.sh 793 B runs code
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.
- 11d ago First seen · 61 lines · 58 tokens per session scan A 5fbba6f58534
sprint-loops is a skill published in the GitHub repository crussella0129/Animus_Sprint_Loops (13 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 627 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
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.
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…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.