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 HECer/yoke --skill yoke-workflowgit clone --depth 1 https://github.com/HECer/yokeWrote 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/hecer/yoke/yoke-workflow)<a href="https://agentmods.dev/skills/hecer/yoke/yoke-workflow"><img src="https://agentmods.dev/badge/skills/hecer/yoke/yoke-workflow/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/hecer/yoke/yoke-workflow"><img src="https://agentmods.dev/badge/skills/hecer/yoke/yoke-workflow.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 | $0.00037 | $0.00572 |
| Opus 5.5 | $0.00015 | $0.00229 |
| Sonnet 5.5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
yoke-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 7d 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.
What it actually says
Yoke Workflow
Provide the same interaction contract in every supported Yoke harness.
- Read
.yoke/config.yaml. If it is missing, offeryoke setup . --host=<current-agent>and run the setup flow before planning. - Plan before starting the loop. Inspect the project, then ask one focused question at a time only where the answer changes product behavior, scope, architecture, security, data ownership, external cost, or an irreversible choice. Include a recommended answer. Resolve routine implementation details yourself.
- Summarize the agreed design in
.yoke/plan.md, including goals, non-goals, constraints, and decisions. Use theauthoring-prdskill to turn it into small stories with testable acceptance criteria. Runyoke prd check .. - Ask once for approval of the complete plan and story set. Do not begin implementation before that approval.
- If
loop.enabledis true, run the stories without routine follow-up questions using the configured runner. Prefer one blockingyoke loop run . --isolatefor the approved backlog. Honor explicitly configured iteration, attempt, cost, and time budgets; do not repeatedly restart capped or blocked runs to bypass them. Do not add--exploreunless the user explicitly requests continuous discovery.- Keep the blocking run attached. If the host needs a separate handoff, use
yoke loop wait . --timeout=60 --json; repeat timeout waits in host code, not through new model turns or repeatedloop statuscalls. Inspect details only for terminal or actionable states. - The host loop owns scheduling, independent checks, review, and integration. Do not create nested orchestration or re-run the same work through overlapping workflow skills.
- Keep the blocking run attached. If the host needs a separate handoff, use
- Respect
loop.decisionPolicy:auto: choose the most suitable option from the plan, current code, and established conventions. Record the interpretation and continue.critical: routine ambiguity is still resolved automatically. If the loop reports a pending critical decision, runyoke loop decision ., present its options and recommendation to the user, ask exactly that question, then runyoke loop answer . --choice=<id> --rationale="<answer>". The answer command records the decision and resumes the same story.
- Never ask whether to run tests, review, commit, or continue to the next approved story. Those are part of the approved workflow.
The user's configured commit identity is authoritative. Do not add an AI co-author unless commit.allowCoAuthors explicitly permits it.
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.
- 7d ago Changed · +2 lines cff477bbd2b6
- 1mo ago Changed 56de73ef3f1b
- 1mo ago First seen · 21 lines · 37 tokens per session scan A a0cfd9fd7ed0
yoke-workflow is a skill published in the GitHub repository HECer/yoke (2 stars, last pushed 8d ago), licensed MIT. It adds 37 tokens to every session and 572 once invoked, about $0.0001 per session on Opus 5.5. 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
ox-cli-session-review
Audit every session in the project ledger for quality, then offer cleanup and regeneration. Carries the operational knowledge from the 2026-04-25 cleanup (the cache-only invariant and a failure-mode watch-list) that no single ox subcommand backs. Use when the user asks to "review the ledger sessions", "audit session…
ox-cli-session-stop
Stop recording and save this agent session to the project ledger.
autopilot-project
A project mode for managing a task DAG, a graph that shows which tasks depend on other tasks. It provides context for the /autopilot status and /autopilot next commands.
report
Activity report from total-agent-memory for a project and period. Use when the user types /report or asks "report for today", "what did we do this week", "weekly / monthly summary", "status report", "retro for project X", "all-time report", "report for last week", or a report for a department or the whole company on…
ox-cli-session-status
Check the status of all active session recordings in this project.
ox-cli-status
Check SageOx project status including authentication, sync, and daemon health.