Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions .agents/skills/poteto-mode/playbooks/multi-phase-plan.md
Original file line number Diff line number Diff line change
Expand Up @@ -32,14 +32,14 @@ Tests alone are not sufficient verification. A PR is verified only when its unit
### Arm the program

- [ ] State the protocol and this plan to the operator, then stop. Start execution only on the operator's explicit go.
- [ ] Workflow sources. Record the installed plugin root and version and read these absolute paths at program start and every audit. Read project-owned resources from the repository's resolved base ref when trunk evidence is required.
- [ ] `<installed poteto-mode directory>/playbooks/<execution playbook>.md`
- [ ] `<installed swarm directory>/SKILL.md`
- [ ] `<resolved control skill path>`
- [ ] `<installed poteto-mode directory>/playbooks/opening-a-pr.md`
- [ ] `<absolute path of each other leaf skill the program uses>`
- [ ] Audit cadence. On the operator's go, audit hourly through an explicitly requested, supported continuation or scheduling facility. Record the actual mechanism. If none is available, record active-session-only execution and the resume command; do not promise unattended ticks.
- [ ] Use this tick prompt, verbatim. "Re-read the execution playbook from its recorded installed path. Audit the operation against it and fix drift in this tick. Probe every active lane and judge progress by side effects only. Stand down a stuck lane and dispatch its replacement now. Then post a short status message to the operator in chat only when the audit found a tracked change that no earlier status message reported, such as a PR opened, a code-ready head, a round launched or closed, a verdict, a merge, a stuck agent and the action taken, a blocker added or cleared, or a decision only the operator can make. Name every such change and nothing else. Do not repeat a table, the merged list, or an unchanged blocker. If the audit found none, end the turn with no reply text. Either way, log this tick's row in your decision trail. The row names the items reported, or none."
- [ ] Read these from trunk at program start. Re-read them at every tick.
- [ ] `git show origin/main:pstack/skills/poteto-mode/playbooks/<execution playbook>.md`
- [ ] `git show origin/main:pstack/skills/swarm/SKILL.md`
- [ ] `git show origin/main:<control skill path>`
- [ ] `git show origin/main:pstack/skills/poteto-mode/playbooks/opening-a-pr.md`
- [ ] `git show origin/main:pstack/skills/<each other leaf skill the program uses>`
- [ ] On the operator's go, arm the audit tick as `/loop 1h` with the tick prompt below. Never leave the cadence to memory.
- [ ] Use this tick prompt, verbatim. "Re-read the execution playbook from trunk. Audit the operation against it and fix drift in this tick. Probe every active lane and judge progress by side effects only. Stand down a stuck lane and dispatch its replacement now. Then post a short status message to the operator in chat only when the audit found a tracked change that no earlier status message reported, such as a PR opened, a code-ready head, a round launched or closed, a verdict, a merge, a stuck agent and the action taken, a blocker added or cleared, or a decision only the operator can make. Name every such change and nothing else. Do not repeat a table, the merged list, or an unchanged blocker. If the audit found none, end the turn with no reply text. Either way, log this tick's row in your decision trail. The row names the items reported, or none."
- [ ] On the operator's hold or stand-down, send every owner a zero-writes order at once.

### Spawn owners
Expand Down
2 changes: 1 addition & 1 deletion .agents/skills/poteto-mode/scripts/check-plan.mjs
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ const SUB_BLOCKS = [
"Merge.",
];
const PROGRAM_H3 = ["Arm the program", "Spawn owners", "PR mechanics", "Verdict and merge", "Boot recipe"];
const PROGRAM_MARKERS = ["Workflow sources.", "Audit cadence.", "status message"];
const PROGRAM_MARKERS = ["git show origin/main:", "/loop 1h", "status message"];
const HOW_TO_READ_MARKERS = [
"One box is one unit of work",
"names the evidence",
Expand Down
21 changes: 3 additions & 18 deletions .agents/skills/poteto-mode/scripts/check-plan.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -20,9 +20,7 @@ ${rule}
### PR mechanics
### Verdict and merge
### Boot recipe
Workflow sources. Read the installed plugin paths recorded in this plan.
Audit cadence. Audit hourly during an explicitly requested Codex continuation, or record active-session-only execution.
Post a status message when tracked state changes.
\`git show origin/main:\` /loop 1h status message

## PR 1
**Depends on.** None.
Expand Down Expand Up @@ -52,10 +50,10 @@ Close.
Recorded.
`;

const runPlan = (example: string, expectedExit: number, plan = validPlan) => {
const runPlan = (example: string, expectedExit: number) => {
const directory = mkdtempSync(join(tmpdir(), "check-plan-test-"));
const file = join(directory, "plan.md");
writeFileSync(file, plan + example);
writeFileSync(file, validPlan + example);
try {
const result = spawnSync("node", [checker, file], { encoding: "utf8" });
expect(result.status).toBe(expectedExit);
Expand All @@ -65,19 +63,6 @@ const runPlan = (example: string, expectedExit: number, plan = validPlan) => {
}
};

test("accepts Codex workflow sources and cadence without Cursor commands", () => {
expect(validPlan).not.toContain("/loop");
expect(validPlan).not.toContain("git show origin/main:");
runPlan("", 0);
});

test("requires workflow sources and an audit cadence", () => {
for (const marker of ["Workflow sources.", "Audit cadence."]) {
const result = runPlan("", 1, validPlan.replace(marker, "Omitted."));
expect(result.stderr).toContain(`Program checklist lacks "${marker}"`);
}
});

test("accepts ordinary, indented, and longer closing fences", () => {
for (const indent of ["", " ", " ", " "])
runPlan(`${indent}\`\`\`markdown\n## Example only\n${indent}\`\`\`\n`, 0);
Expand Down
Loading