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.
git clone --depth 1 https://github.com/srnichols/plan-forgeWrote 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/commands/srnichols/plan-forge/step4-completeness-sweep)<a href="https://agentmods.dev/commands/srnichols/plan-forge/step4-completeness-sweep"><img src="https://agentmods.dev/badge/commands/srnichols/plan-forge/step4-completeness-sweep/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/commands/srnichols/plan-forge/step4-completeness-sweep"><img src="https://agentmods.dev/badge/commands/srnichols/plan-forge/step4-completeness-sweep.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 | $0.00024 | $0.00599 |
| Opus 5 | $0.00012 | $0.00300 |
| Sonnet 5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
step4-completeness-sweep 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 today.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 4: Completeness Sweep
Pipeline: Step 4 of 5 (Session 2 — Execution)
When: After all slices pass (Step 3), before the Review Gate
Model suggestion: Any model / Copilot Auto (10% token savings) — pattern scanning works well on all models
Next Step:step5-review-gate.prompt.md(new session)
Replace <YOUR-HARDENED-PLAN> with your hardened plan filename.
Read these files first:
- docs/plans/AI-Plan-Hardening-Runbook.md (Section 6.1)
- docs/plans/.md (Definition of Done)
- .github/copilot-instructions.md
Now act as a COMPLETENESS SWEEP AGENT (see Section 6.1 of the runbook).
Scan ALL files created or modified during this phase for:
- TODO, HACK, FIXME comments
- Mock/placeholder/stub data (hardcoded records, fake values)
- "will be replaced" / "Simulate" / "Seed with sample" comments
- Stub implementations (methods that return defaults / do nothing)
- Commented-out code with future intent
For each finding:
- Wire it to the real service/API/method
- Remove the deferred-work comment
- Verify build + tests pass after each batch
Output:
- Findings count (before → after)
- Files modified
- New methods/types added
- Build: pass/fail
- Tests: pass/fail
If ANY finding cannot be resolved without scope expansion: pause and report the blocker.
MCP Tools (if Plan Forge MCP server is running)
- Run sweep: call
forge_sweepfor structured TODO/FIXME/stub scanning with file locations - Verify scope: call
forge_diffwith the plan file to confirm all changes are within scope before handoff to review
Use MCP tools for structured results when available. Fall back to manual grep if MCP is not configured.
Persistent Memory (if OpenBrain is configured)
- Before sweeping:
search_thoughts("common stubs", project: "<YOUR PROJECT NAME>", created_by: "copilot-vscode", type: "bug")— check if prior sweeps found recurring stub patterns so you can look for them proactively - After sweep:
capture_thoughts([...findings], project: "<YOUR PROJECT NAME>", created_by: "copilot-vscode", source: "plan-forge-step-4-sweep", type: "convention")— batch capture patterns and conventions discovered during cleanup
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.
- today First seen · 59 lines · 24 tokens per session scan A aad84cbdd5bb
step4-completeness-sweep is a command published in the GitHub repository srnichols/plan-forge (5 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 599 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 2026-09-08.
Other commands, from other repositories
sdd-continue
Continue the next SDD phase in the dependency chain.
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-status
Show structured SDD status for an active change.
sdd-new
Start a new SDD change — runs exploration then creates a proposal.
skill-creator
Create or update an OpenCode skill using the bundled skill-creator workflow.
harness-review
Review the current change set from an opposing harness-engineering perspective.