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/ilyasibrahim/claude-agents-coordinationWrote 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/ilyasibrahim/claude-agents-coordination/debt)<a href="https://agentmods.dev/commands/ilyasibrahim/claude-agents-coordination/debt"><img src="https://agentmods.dev/badge/commands/ilyasibrahim/claude-agents-coordination/debt.svg" alt="Measured on agentmods" 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 | $0.00006 | $0.00590 |
| Opus 5 | $0.00003 | $0.00295 |
| Sonnet 5 | $0.00001 | $0.00118 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade B, and why
debt scanned grade B with 1 finding 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Get next TD number: `grep -oE 'TD-[0-9]+' .claude/reports/_tech-debt.md | sort -t- -k2 -n | tail -1` How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Debt Command
Manage technical debt tracking.
Usage
/debt # View debt summary
/debt add [description] # Add new debt item
/debt resolve [TD-NNN] # Mark item resolved
/debt review # Full registry review
View Summary
/debt
Read .claude/reports/_tech-debt.md and display:
# Tech Debt Summary
## By Priority
| Priority | Count | Oldest |
|----------|-------|--------|
| Critical | [n] | [date] |
| High | [n] | [date] |
| Medium | [n] | [date] |
| Low | [n] | [date] |
## Critical Items (Immediate Attention)
[List critical items]
## Recommendations
- [If critical > 0]: Address critical debt before new features
- [If oldest > 90 days]: Review and reprioritize stale items
Add Debt
/debt add "Description" --priority [critical|high|medium|low]
- Get next TD number:
grep -oE 'TD-[0-9]+' .claude/reports/_tech-debt.md | sort -t- -k2 -n | tail -1 - Add to appropriate section
- Report confirmation
Resolve Debt
/debt resolve TD-NNN
- Find item in registry
- Mark as
[x] - Move to Resolved section
- Add resolution date
- Update metrics
Full Review
/debt review
Invoke analysis:
Task(code-quality, "
Mode: qa-strategy
Audit tech debt registry at .claude/reports/_tech-debt.md
Assess:
1. Are priorities accurate?
2. Any items that should be escalated?
3. Stale items (>90 days without progress)?
4. Items that may no longer be relevant?
5. Missing debt items based on codebase review?
Output recommendations for registry cleanup.
")
Integration
Tech debt is created from:
/postmortemaction items/review-fullfindings marked "won't fix now"/rfcdeferred requirements- Sprint retrospectives
Debt Types
| Type | Example | Typical Priority |
|---|---|---|
| Code | Duplicated logic, missing abstractions | Medium |
| Test | Low coverage, flaky tests | High |
| Dependency | Outdated packages, deprecated APIs | High |
| Architecture | Scaling limits, tight coupling | Critical |
| Documentation | Missing docs, stale docs | Low |
| Infrastructure | Manual processes, missing automation | Medium |
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.
- 7d ago First seen · 110 lines · 6 tokens per session scan B 3b9044825cd4
debt is a command published in the GitHub repository ilyasibrahim/claude-agents-coordination (83 stars, last pushed 3mo ago), licensed Unlicense. It adds 6 tokens to every session and 590 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.