CourseForge
CLAUDE.md0 starsChanged 55 days agoMITView on GitHub
CourseForge is a TypeScript/Node course-engineering harness: a deterministic 11-stage pipeline (concept → research → design → storyboard → editorial → visual direction → model → build → QA → release) that uses Claude Code or Codex for semantic work and code for routing, validation, rendering, QA and release decisions. Keep this file consistent with AGENTS.md. 1. Provider-neutral core: only src/harness/** names the claude/codex CLIs, flags or output formats. 2. Only src/core/proc.ts imports child_process (cross-spawn, shell: false, prompts on stdin). 3.…
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-reviewSkill
- alignment-reviewSkill
- assessment-designSkill
- assessment-reviewSkill
- course-gap-analysisSkill
- editorial-humanizationSkill
- fact-checkSkill
- html-intake-reviewSkill
- instructional-designSkill
- instructional-graphicsSkill
- research-authoringSkill
- research-planningSkill
- research-reviewSkill
- scenario-designSkill
- storyboard-authoringSkill
- ui-reviewSkill
- ux-reviewSkill
- visual-directionSkill
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Keep this file consistent with AGENTS.md.
- Very specific: line 48
Only src/core/proc.ts imports child_process (cross-spawn, shell: false, prompts on stdin).
- Very specific: line 56
No global dependencies: never read or modify ~/.claude, ~/.codex or global npm config.
- Distinctive: line 57
No secrets, tokens, personal paths or emails in code, fixtures, logs or docs.
- Very specific: line 64
Do not run npm install, commit, stash or check out unless asked.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CourseForge: instructions for Claude Code
CourseForge is a TypeScript/Node course-engineering harness: a deterministic 11-stage pipeline (concept →
research → design → storyboard → editorial → visual direction → model → build → QA → release) that uses Claude
Code or Codex for semantic work and code for routing, validation, rendering, QA and release decisions.
Keep this file consistent with AGENTS.md.
Sources of truth
docs/exec-plans/active/courseforge-v1.md: the approved plan (architecture, decisions, test mapping)docs/architecture/: how the system works as built;docs/adr/: recorded deviationsdocs/bootstrap/: original requirements of record (read-only; do not treat as runtime code)config/*.json: registries (stages, reviewers, skills, tools, routing, fallbacks, review policy)src/core/schemas/: zod schemas for every artifact and agent output.claude/rules/: path-scoped rules (architecture.mdforsrc/,courses.mdforcourses/,testing.md)
Map
| Path | Contents |
src/cli, src/environment | CLI (help.ts lists commands and exit codes), doctor/setup |
src/pipeline | State machine, stage loop (run-stage.ts), stage handlers, write audit, public API (api.ts) |
src/routing | Pure router: execution plans, backend selection, gates, visual routes |
src/harness | Claude/Codex/fake adapters, prompt assembly, recording (only place that knows the CLIs) |
src/review, src/release | Findings, adjudication, repair plans, scoped repair; release gate and reports |
src/ingestion, src/artifacts | Any-stage import; artifact registry, versions, locks, trace graph |
src/graphics, src/renderer, components/course-ui | Renderers, single-file HTML compiler, UI components and runtime |
src/qa | Playwright contract runner, crawler, axe, regression |
prompts/templates, prompts/rubrics, .claude/skills | Prompt data (never embed prompt prose in TypeScript) |
courses/<id>/ | One self-contained course project each |
Commands
npm run build # tsc → dist/
npm run typecheck
npm run lint # Biome; npm run format to fix
npm test # unit + integration (offline, fake harness)
npm run test:e2e # Playwright
npm run test:acceptance
npm run gen:schemas # after changing src/core/schemas
node bin/courseforge.mjs <command> # or ./courseforge, .\courseforgeNon-negotiables
- Provider-neutral core: only
src/harness/**names theclaude/codexCLIs, flags or output formats. - Only
src/core/proc.tsimportschild_process(cross-spawn,shell: false, prompts on stdin). - Deterministic routing: stages, reviewers, skills, tools, renderers and fallbacks come from
config/viasrc/routing. Agents return closed enums; code maps them to tools. Plans are saved before agent work. - zod schemas are the source of truth. After changing one, run
npm run gen:schemasand commitschemas/. Agent-facing schemas stay flat and strict (all required, optional = nullable, no$ref). - Course isolation: course reads/writes stay under
courses/<id>/, throughsrc/core/fsx.tshelpers. - Preserve human work: never edit
input/originals/,versions/, locked artifacts or locked IDs; agent steps run inside the write audit, which must not be bypassed. - No global dependencies: never read or modify
~/.claude,~/.codexor global npm config; no global installs. - No secrets, tokens, personal paths or emails in code, fixtures, logs or docs.
Parallel work
- Work only in the directories you were assigned; do not edit other streams' files.
- The coordinator alone edits
package.json, the lockfile,tsconfig*.json,biome.json, test runner configs and shared interfaces (src/core/*,src/harness/types.ts,src/pipeline/api.ts). - Do not run
npm install, commit, stash or check out unless asked. Do not run e2e while other browser or agent-pool work is running (limited RAM).
Before you say you are done
npm run typecheck,npm run lint,npm testpass.npm run test:e2epasses if you touched the renderer, components, runtime, graphics or QA.- Schema changes:
npx tsx scripts/gen-schemas.ts --checkpasses. - New or changed tests covering a requirement carry its acceptance tag (
@C6 …). - Docs in
docs/still describe the code; UI changes were checked in a real browser.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

