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 skills add rp1-run/rp1 --skill tech-debt-collectorgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/skills/rp1-run/rp1/tech-debt-collector)<a href="https://agentmods.dev/skills/rp1-run/rp1/tech-debt-collector"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/tech-debt-collector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rp1-run/rp1/tech-debt-collector"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/tech-debt-collector.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.04084 |
| Opus 5 | $0.00019 | $0.02042 |
| Sonnet 5 | $0.00008 | $0.00817 |
| Haiku 4.5 | $0.00004 | $0.00408 |
Grade A, and why
tech-debt-collector 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 3d 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Debt Collector Orchestrator
Role: Pure orchestrator for evidence-gated tech debt and software bloat detection.
This workflow identifies candidate tech debt signals via a scout agent, clusters discoveries by root cause, ranks by materiality using burden signals, validates claims via hypothesis-tester, and produces a final report with up to 5 findings, each with concrete remediation actions and rollback plans.
Key Constraints:
- Analysis-only: no source code edits or project state changes
- Scope: supports whole project, specific file path, branch, or PR diff
- Output: 0-5 findings per run (0 findings is valid success)
- Confidence: C1-C4 ordinal tier system only (no C5)
- Non-destructive runs: work artifacts (
hypotheses.md,leads.json,report.md) live at fixed paths underfeatures/tech-debt-collector/; at run start any prior versions are archived intofeatures/tech-debt-collector/runs/<prior-run-id>/(§1.4) before the new run writes, so completed runs remain retrievable
§CTX: Use the pre-resolved SCOPE, LENS, RUN_ID, projectRoot, kbRoot, workRoot, and codeRoot values from the generated Workflow Bootstrap section. Do not hardcode .rp1/work/ or .rp1/context/ paths.
References
| File | Purpose | When to Load |
|---|---|---|
references/validation-scoring.md |
C1-C4 confidence tiers, evidence caps, C3+ promotion gate | Validating phase, after §3.3 collects hypothesis-tester results |
references/report-format.md |
Finding template, section ordering, artifact registration | Reporting phase, after §4.1 emits the reporting state |
references/run-archival.md |
Archiving a prior run's artifacts | Scoping phase, only when prior-run artifacts exist |
references/scope-resolution.md |
SCOPE classification order, PR-reference forms, cross-repository guard | Scoping phase, at §1.1 |
references/lead-processing.md |
Root-cause clustering and materiality ranking | Scouting phase, once the scout returns leads |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 370 lines · 38 tokens per session scan A 2480a8b86945
tech-debt-collector is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 4,084 once invoked, about $0.0002 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 2026-09-07.
Other skills, from other repositories
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
codebase-cleanup-refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
eslint-fix
A project-aware assistant for finding and fixing ESLint errors, warnings, and configuration compatibility problems. ESLint is a tool that checks JavaScript and TypeScript code for style and common mistakes.