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.
npx agentmods add commands/legacybridge-tech/claude-plugins/teds-completegit clone --depth 1 https://github.com/legacybridge-tech/claude-pluginsWhat 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 | $0.00007 | $0.01250 |
| Opus 5 | $0.00003 | $0.00625 |
| Sonnet 5 | $0.00001 | $0.00250 |
| Haiku 4.5 | $0.00001 | $0.00125 |
Grade A, and why
teds-complete 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 2d ago.
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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Complete TEDS Task
Launch the teds-archiver agent to complete and archive a finished TEDS task.
Usage
/teds-complete task-id
Examples
# Complete a specific task
/teds-complete 20250116-1430-refactor-auth
# List tasks first, then complete
/teds-status
/teds-complete 20250115-0920-migrate-db
What This Does
The archiver agent will:
- Verify completion against success criteria in
plan.md - Ask for confirmation if any criteria are incomplete
- Finalize documentation:
- Add completion entry to
execution_log.md - Update
status.yaml: set status to "completed" - Summarize all learnings in
knowledge_base.md - Set completion timestamp in
manifest.yaml
- Add completion entry to
- Extract knowledge:
- Create summary document in
knowledge_index/[task-id]-summary.md - Include: objectives, approach, learnings, outcomes
- Create summary document in
- Archive task:
- Move from
active_tasks/toarchived_tasks/ - Preserve complete directory structure
- Move from
- Update tracking:
- Add entry to workspace task history
Verification Process
Before archiving, the agent checks:
Reviewing task completion...
Success Criteria (from plan.md):
✅ All OAuth providers integrated (Google, GitHub)
✅ Tests passing with >90% coverage
✅ Documentation updated
⚠️ Performance benchmarks not run
Incomplete: 1 criterion
Options:
1. Complete anyway (mark as acceptable)
2. Continue task to finish remaining work
3. Cancel and return to task
Choose [1/2/3]:
Completion Report
After successful archival:
# Task Completed: refactor-auth
**Task ID**: 20250116-1430-refactor-auth
**Duration**: 2025-01-16 14:30 to 2025-01-18 16:45
**Total Time**: ~12 hours over 2 days
**Status**: Successfully completed
## Key Outcomes
✅ OAuth 2.0 authentication fully implemented
✅ Google and GitHub providers integrated
✅ Comprehensive test suite (94% coverage)
✅ Documentation complete with examples
✅ Migration guide for existing users
## Key Learnings
1. **Google OAuth Setup**
- Requires web credentials, not service account
- Redirect URIs must match exactly (including trailing slash)
2. **Token Management**
- Refresh tokens expire after 6 months if unused
- Implemented automatic refresh 5 minutes before expiration
3. **Security Considerations**
- PKCE extension essential for public clients
- State parameter prevents CSRF attacks
4. **Testing Insights**
- Mock OAuth providers for unit tests
- Integration tests need real credentials (use staging)
## Statistics
- **Files Modified**: 23
- **Tests Added**: 47
- **Documentation Pages**: 8
- **Checkpoints Created**: 6
- **Knowledge Entries**: 12
## Files Archived
- **Location**: claude_work_space/archived_tasks/20250116-1430-refactor-auth/
- **Summary**: claude_work_space/knowledge_index/20250116-1430-refactor-auth-summary.md
## Reusable Components
The following patterns can be applied to future tasks:
- OAuth provider abstract class design
- Token refresh mechanism
- Integration testing strategy
---
Task successfully archived. Knowledge preserved for future reference.
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.
- 2d ago First seen · 208 lines · 7 tokens per session scan A 244570919f06
teds-complete is a command published in the GitHub repository legacybridge-tech/claude-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 1,250 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.