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 agentmods add skills/beyondeye/aitasks/task-workflow-remotenpx skills add beyondeye/aitasks --skill task-workflow-remotegit clone --depth 1 https://github.com/beyondeye/aitasksWhat 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 | $0.00023 | $0.22287 |
| Opus 5 | $0.00012 | $0.11144 |
| Sonnet 5 | $0.00005 | $0.04457 |
| Haiku 4.5 | $0.00002 | $0.02229 |
Grade A, and why
task-workflow 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
32 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.
- agent-attribution.md 1.5 KB
- auto-verification.md 6.4 KB
- build-verification.md 5.4 KB
- code-agent-commit-attribution.md 2.0 KB
- contributor-attribution.md 3.7 KB
- crash-recovery.md 5.7 KB
- cross-repo-child-assignment.md 8.0 KB
- execution-profile-selection-auto.md 3.1 KB
- execution-profile-selection.md 3.8 KB
- gate-cli.md 3.1 KB
- issue-update.md 2.5 KB
- lock-release.md 1.0 KB
- manual-verification-followup.md 5.0 KB
- manual-verification.md 14 KB
- merge-broker.md 28 KB
- merge-target-sync.md 5.9 KB
- model-self-detection.md 3.1 KB
- plan-approved-stop.md 5.4 KB
- plan-externalization.md 14 KB
- planning-cross-repo.md 8.5 KB
- planning.md 29 KB
- pr-close-decline.md 1.1 KB
- profiles.md 15 KB
- related-task-discovery.md 4.7 KB
- remote-drift-check.md 7.9 KB
- repo-structure.md 2.1 KB
- risk-evaluation.md 5.6 KB
- risk-mitigation-followup.md 31 KB
- satisfaction-feedback.md 5.2 KB
- task-abort.md 7.6 KB
- task-creation-batch.md 7.5 KB
- upstream-followup.md 7.2 KB
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.
- yesterday First seen · 966 lines · 23 tokens per session scan A 043eba0442b0
task-workflow is a skill published in the GitHub repository beyondeye/aitasks (8 stars, last pushed 2d ago), with no licence file. It adds 23 tokens to every session and 22,287 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
execution
M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。.
fix-self-check
M-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。.
review
M-1.5 review skill — 在 patch 跟 contract 之间找 finding，produce Finding 一等对象。.
om-prepare-test-env
Cezar is a parallel coding agents orchestrator. Type a task, pick a workflow and an agent — Claude Code, Codex or OpenCode, or a mix of them per step — and watch it work live: steps, tool calls ... or: fire and forget, PR will land and issue will be fixed. Run ot locally (Linux, Mac, WSL2) or on VPS!
dependency-analyze
从 task 的 read/write set + concept statemachine 推导 6 种依赖类型的提案。主 planner 决定边的真实性。派它时只给 read/write set 与疑点、不给预期边集；已有预判逐条标「待复核」交它取证。.
execution-self-check
Pre-submit 自检——envelope 提交 commit gate 前必跑。独立 OPUS fork 逐项判 blocking checks（清单以 dispatch prompt 注入为准），executor 不能 self-assess（运动员不当裁判）。.