tdmcp-interactive-projection-mapping-611bed — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited tdmcp-interactive-projection-mapping-611bed (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Coordinate the dedicated team for the approved interactive projection mapping feature. This skill specializes the generic tdmcp pipeline for a physical camera/projector feature where synthetic tests, live TD checks, and honest calibration language all matter.
This repo documents that the current environment runs teams as coordinated sub-agents rather than TeamCreate. Use a hybrid sub-agent workflow:
| Phase | Mode | Reason |
|---|---|---|
| Plan | local lead or interactive-projection-lead | keep scope tied to the approved spec. |
| Prototype + tool build | parallel sub-agents | live prototype and isolated tool file have disjoint write scopes. |
| Integrate/docs | single-writer sub-agent | registries, CLI, recipes, and docs are shared files. |
| QA/fix loop | sub-agent fan-in | QA routes precise defects to the owner; no release without PASS/UNVERIFIED accounting. |
All spawned agents use model: "opus" unless the user explicitly asks for a different model.
| Agent | Role | Skills | Output |
|---|---|---|---|
interactive-projection-lead | scope owner and wave captain | this skill | _workspace/interactive-projection/00_plan.md |
interactive-projection-prototyper | TD live/synthetic prototype and calibration findings | tdmcp tools | _workspace/interactive-projection/01_prototype.md |
interactive-projection-tool-builder | new Layer 1 tool file + focused unit test | td-feature-build | _workspace/interactive-projection/02_build_tool.md |
interactive-projection-integrator | single-writer registry, CLI, recipe, docs | td-feature-integrate | _workspace/interactive-projection/03_integrate.md |
interactive-projection-qa | offline gates, boundary QA, live TD validation | td-feature-qa | _workspace/interactive-projection/04_qa.md |
Use existing tdmcp-bridge-engineer only if implementation proves that a new bridge REST endpoint is necessary. The default plan should avoid a new endpoint.
Read these before changing code:
docs/superpowers/specs/2026-06-05-interactive-projection-mapping-design.mdAGENTS.mdsrc/tools/layer1/createMotionReactive.tssrc/tools/layer1/createBlobReactive.tssrc/tools/layer1/createProjectionMapping.tssrc/tools/layer1/createOpticalFlow.ts when presentrecipes/optical_flow_particles.jsonrecipes/projection_mapping.jsonrecipes/particle_system_basic.jsongit status --short._workspace/interactive-projection/.affected phase;
timestamp before starting a new one.
get_td_info before any live prototype or QAclaim.
Create _workspace/interactive-projection/00_plan.md with:
Default slice order:
Run in parallel when both are in scope:
interactive-projection-prototyper: use tdmcp live tools to prove or plan theTD network. If bridge is offline, produce a live-prototype checklist instead.
interactive-projection-tool-builder: create only the new tool file and itsfocused unit test. Do not edit shared files.
Both agents must write their _workspace/interactive-projection/0*_*.md notes.
Invoke interactive-projection-integrator after the tool builder reports export names. It owns all shared files:
src/tools/layer1/index.ts;src/cli/agent.ts;recipes/interactive_projection_mapping.json if the recipe slice is active;The integrator must run npm run typecheck and npm run build. If docs/recipes changed, also run npm run validate:recipes and the docs generation/build gate that matches the touched files.
Invoke interactive-projection-qa incrementally:
QA sends precise defects to the owner and re-validates after fixes. Cap repeated fix loops at 2-3 rounds, then report the blocker.
Report:
Do not tag, release, or push unless the user explicitly asks.
approved spec
-> lead plan
-> prototyper notes ---------+
-> isolated tool builder ----+-> integrator -> qa -> fixes -> final report| Situation | Strategy |
|---|---|
| Bridge offline | Build/test offline; mark live checks UNVERIFIED pending bridge. |
| Camera permission modal | Pause live camera claims; keep synthetic source path green. |
| Blob tracker unavailable | Ship motion-first MVP with warning; keep blob branch as follow-up. |
| Shared-file conflict | Stop shared edits and ask the lead to reconcile. |
| QA fail after 3 rounds | Hold the failing slice; report evidence and next fix. |
User says "continue the interactive projection mapping implementation." The orchestrator reads the spec, creates _workspace/interactive-projection/00_plan.md, spawns prototype and tool-builder work, integrates the tool and CLI, runs typecheck/build/focused tests, validates synthetic TD output if the bridge is up, and reports physical projector QA as PASS or UNVERIFIED.
The bridge is offline and the blob tracker is not known to be createable. The orchestrator still builds the synthetic-safe tool and docs, QA marks live camera and blob checks UNVERIFIED, and the final report names the exact command to rerun when TouchDesigner is open.
Should trigger:
Should not trigger:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.