atproto Thingiverse but good
skill updates
+9
-8
+1
-1
.polytoken/facets/design.md
+1
-1
.polytoken/facets/design.md
···
44
44
45
45
When a goal becomes an executable slice, make sure it has goal/non-goals, relevant files/contracts, verified facts, steps or constraints, validation, risks/open decisions, and review expectations.
46
46
47
-
For small, immediate implementation handoffs, you may use `write_plan` and `handoff_plan` directly, but run the handoff review gate first: at least one `code-reviewer`; for larger plans, the three-reviewer panel with pinned `model_override` values `codex/gpt-5.5(medium)`, `anthropic/claude-opus-4-8(medium)`, and `zai/glm-5.2(max)`. Fix or rebut every Critical/High finding, re-run until clean, and stop for operator input if a pinned model does not resolve.
47
+
For small, immediate implementation handoffs, you may use `write_plan` and `handoff_plan` directly, but run the handoff review gate first: at least one `code-reviewer`; for larger plans, the three-reviewer panel with pinned `model_override` values `codex/gpt-5.5(medium)`, `anthropic/claude-opus-4-8(medium)`, and `zai/glm-5.2(max)`. Fix or rebut every Critical/High finding, re-run until clean, and stop for operator input if a pinned model does not resolve. Ensure you tell the reviewer the exact absolute path to the plan file to read it.
48
48
49
49
For larger implementation planning, switch to `plan` so the dedicated planning facet can produce and review the execution handoff.
+1
.polytoken/facets/plan.md
+1
.polytoken/facets/plan.md
···
26
26
- For small/simple handoffs, run at least one `plan-reviewer` subagent against the handoff plan.
27
27
- For larger plans, run three reviewers in parallel using `code-reviewer` with `model_override` values `codex/gpt-5.5(medium)`, `anthropic/claude-opus-4-8(medium)`, and `zai/glm-5.2(max)`.
28
28
- If a pinned `model_override` does not resolve at runtime, stop and ask the operator; do not silently substitute a weaker model.
29
+
- ensure you tell the reviewer the exact absolute path to the plan file to read it.
29
30
- Fix or rebut every Critical/High finding with evidence. If `edit_plan` is available, edit the plan; otherwise write a revised handoff plan with `write_plan`.
30
31
- Re-run the same reviewer set while any reviewer returns any Critical or High finding.
31
32
- Only call `handoff_plan` when all reviewers report zero Critical and zero High findings, or when the operator explicitly accepts the risk.
+3
-3
.polytoken/project_vars.yaml
+3
-3
.polytoken/project_vars.yaml
+2
-2
.polytoken/skills/jira-solo-tasker-execute/SKILL.md
+2
-2
.polytoken/skills/jira-solo-tasker-execute/SKILL.md
···
100
100
101
101
Run the configured reviewer set. Default panel:
102
102
103
-
- `code-reviewer` with `model_override` `codex/gpt-5.5(high)`
104
-
- `code-reviewer` with `model_override` `anthropic/claude-opus-4-8(medium)`
103
+
- `code-reviewer` with `model_override` `codex/gpt-5.5(medium)`
104
+
- `code-reviewer` with `model_override` `codex/gpt-5.4-mini(xhigh)`
105
105
- `code-reviewer` with `model_override` `zai/glm-5.2(max)`
106
106
107
107
Ask reviewers for Critical/High/Medium/Low findings, with evidence and suggested fixes.
+1
-1
.polytoken/skills/jira-solo-tasker-plan/SKILL.md
+1
-1
.polytoken/skills/jira-solo-tasker-plan/SKILL.md
···
125
125
Before `handoff_plan`, run three `plan-reviewer` subagents in parallel with the configured/pinned models:
126
126
127
127
- `codex/gpt-5.5(medium)`
128
-
- `anthropic/claude-opus-4-8(medium)`
128
+
- `codex/gpt-5.4-mini(xhigh)`
129
129
- `zai/glm-5.2(max)`
130
130
131
131
Fix or rebut every plan finding with evidence. Re-run the same reviewer set while any reviewer returns any Critical or High finding.
+1
-1
.polytoken/subagents/code-reviewer.md
+1
-1
.polytoken/subagents/code-reviewer.md
···
3
3
description: Adversarial reviewer for implementation plans, code changes, tests, and shipping quality. Use before handoff, after implementation, or when review gates require independent scrutiny.
4
4
polytoken:
5
5
model: default_model:full
6
-
tools: [file_read, grep, glob, shell_exec, skill]
6
+
tools: [file_read, grep, glob, shell_exec, skill, mcp__atlassian]
7
7
undeferred_tools: [file_read, grep, glob]
8
8
skills_allow: ["reviewing-code-for-shipping-quality", "polytoken:investigating-a-codebase"]
9
9
---