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/w2ur/claude-code-setup/tech-debtgit clone --depth 1 https://github.com/w2ur/claude-code-setupWhat 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 | $0.00076 | $0.01688 |
| Opus 5 | $0.00038 | $0.00844 |
| Sonnet 5 | $0.00015 | $0.00338 |
| Haiku 4.5 | $0.00008 | $0.00169 |
Grade A, and why
tech-debt 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 yesterday.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monthly technical health review. Two phases: triage everything, then deep-dive on your picks.
Mode Selection
- If
$0is empty: run Phase 1 (triage all) → present priority list → ask owner to pick → run Phase 2 (deep review). - If
$0is--triage-only: run Phase 1 only, no fixes. - If
$0is app names (e.g.,my-budget-app my-bias-app): skip Phase 1, run Phase 2 directly on those apps.
Phase 1 — Fast Triage (~1 min for all apps)
Phase 1 is fully deterministic, so it is a script and not model work (CLAUDE.md: deterministic work gets a script, no model). Run it and present its output:
bash ~/.claude/scripts/tech-debt-triage.sh
It scans every git repo in ~/Dev (via dev-scanner.sh --json), scores each on the four signals below, and prints a ranked markdown table ready to show the owner. --json gives the same data machine-readable. It is read-only — it never writes the rotation tracker, because "last scan" means last deep review, not last triage.
| Signal | Source | Weight |
|---|---|---|
| A — commit activity | git log --since="30 days ago" |
2 if >10, 1 if 1–10, 0 if none |
| B — portfolio prominence | position of repo: '<name>' in editorial.ts (Layer 3, M12) |
2 if in the first 6, 1 if present later, 0 if absent |
| C — time since last deep review | ~/Dev/.tech-debt-rotation.json |
3 never, 2 if >60d, 1 if 30–60d, 0 if <30d |
| D — quick issues | npm outdated, npm audit, console.log count, .nvmrc |
+1 per high/critical vuln, +1 if >5 outdated, +1 if >3 console.log |
Do not re-implement these signals inline. The script is the single source of truth for the scoring; restating the weights here in runnable form is exactly how the two drift apart.
Exit codes: 0 clean · 2 ran but degraded (a required tool was missing, so the numbers are incomplete — say so before presenting them) · 1 hard error.
Then ask: "Which apps do you want me to review in depth? (names or numbers, or 'top N')"
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.
- yesterday First seen · 183 lines · 76 tokens per session scan A fed41dbf75a2
tech-debt is a command published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 1,688 once invoked, about $0.0004 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
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
icon-lookup
Search for icons by name, or identify a PUA character.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
roadmap
Generate or update a per-release roadmap from the PRD and analysis documents. Triages features, groups into phases, and produces a structured roadmap.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
adr
Architecture Decision Record (ADR) command. Documents architectural decisions in a structured format.