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/phj128/autoworker/checkpointnpx skills add phj128/autoworker --skill checkpointgit clone --depth 1 https://github.com/phj128/autoworkerWrote 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/phj128/autoworker/checkpoint)<a href="https://agentmods.dev/skills/phj128/autoworker/checkpoint"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/checkpoint.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 | $0.00050 | $0.00737 |
| Opus 5 | $0.00025 | $0.00368 |
| Sonnet 5 | $0.00010 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
checkpoint 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 5d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autoworker:checkpoint — Record Progress (Phase Check-off / Test Results)
Called after every autoworker:code or autoworker:test completion. Performs different record-keeping based on upstream type, then always calls autoworker:dispatch.
Execution Flow
1. Locate Subtask
Glob `subtask_*.md` (exclude subtask_template.md) →
0 found → stop, prompt to create subtask
1 found → use directly (backward compatible)
multiple → grep `status:` to filter:
- Files without status field treated as active (backward compatible)
- Exactly 1 active → use it
- 0 active → list all files + status, prompt user to choose
- >1 active → report anomaly
→ Read → locate "## Plan", "## Verification Plan", and "## Test Results" sections
2. Determine Upstream Type
Prioritize conversation context; when context is insufficient, infer from file state:
- Upstream is autoworker:code: Conversation contains Phase implementation content; or file has unchecked Phase with corresponding code files already modified
- Upstream is autoworker:test: Conversation contains test execution output; or file has all Phases checked but incomplete test layers
3a. Upstream is autoworker:code → Phase Check-off
- Extract the just-completed Phase number and Step list from conversation context
- Edit subtask's "Plan" section: check off all Steps for that Phase
[x] - Append completion record in "Progress Log" section:
**Phase X complete**
<brief change description>
3b. Upstream is autoworker:test → Test Results Write
- Extract test level and per-item results from conversation context
- Edit subtask's "Test Results" section, format:
### L<N>
- `<command>`: <output summary> PASS/FAIL
- Check off passed items
[x]in the "Verification Plan" section
4. Judgment Criteria
Hard standard for "pass":
- Function completes expected task and returns meaningful results
- Returning empty array/empty string without error ≠ pass
- "No exception thrown" ≠ pass
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.
- 5d ago First seen · 83 lines · 50 tokens per session scan A cd75ccb34075
checkpoint is a skill published in the GitHub repository phj128/autoworker (17 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 737 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
flow-next-interview
In-depth Q&A to refine a spec, task, or spec file before building. Use when asked to flesh out, refine, or interrogate requirements.
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-land
Autonomous PR babysitter tick. Fixes CI, resolves feedback, merges when converged, closes the spec, releases. Emits LANDVERDICT. Use when asked to land PRs.
flow-next-plan
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).
flow-next-spec-completion-review
Verify that a spec's completed tasks fully implement the spec requirements. Use at spec completion before close.
flow-next-guide
Recommend the smallest sufficient flow-next workflow from the starting state. Stateless router. Use when unsure which command or stage applies next.