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/nicelight/devrails-26/tech-debtgit clone --depth 1 https://github.com/nicelight/DevRails-26What 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 | $0.00013 | $0.00572 |
| Opus 5 | $0.00006 | $0.00286 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
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 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.
What it actually says
/tech-debt - Advisory technical-debt report
<input_contract> Invocation provides exactly one review intent:
/tech-debt FT-<NNN>
/tech-debt wave <N>
/tech-debt <explicit path, diff, or change scope>
/tech-debt repo-wide
Resolve a feature or wave through the relevant indexed task records, durable
evidence, and actual changed files. touched_files is advisory and does not
prove the complete change surface.
repo-wide is valid only when explicitly requested. Do not widen a feature,
wave, path, diff, or other explicit scope to repository-wide review.
</input_contract>
<hard_invariants>
- Create exactly one new Markdown report under
PAPERCUTS/TECHDEBTS/. - Never overwrite an existing report. Use a new collision-free filename; add a numeric suffix when the preferred filename already exists.
- Do not write or modify any other project file.
- Do not create or change requirements, features, tasks, specs, statuses, lifecycle state, blockers, gates, verdicts, resume routes, dashboards, registries, scheduler state, or a debt lifecycle.
- Do not launch another skill or agent.
- A report with no material findings is a successful result. </hard_invariants>
<finding_admission> Include a finding only when the inspected evidence shows an observable debt mechanism with material impact on repeated change cost, coupling, regression risk, reliability, or maintenance burden.
Style preference, function size, coverage percentage, dependency age, or absent documentation alone is not a finding. Do not invent findings when evidence is insufficient; record the uncertainty instead. </finding_admission>
<required_outputs> The report records:
- the exact checked scope;
- evidence and precise locations;
- confirmed findings, if any;
- practical impact, relative priority, and the smallest remediation direction;
- uncertainty where the evidence does not support a confident conclusion.
If no material debt is confirmed, state that explicitly and leave the findings section empty. </required_outputs>
<handoff_contract>
- Successful report -> return the report path and whether material findings were confirmed.
- The report never blocks, repairs, promotes, or routes workflow state. </handoff_contract>
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 · 76 lines · 13 tokens per session scan A f1be25509a77
tech-debt is a command published in the GitHub repository nicelight/DevRails-26 (22 stars, last pushed 5d ago), licensed MIT. It adds 13 tokens to every session and 572 once invoked, about $0.0001 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 2026-08-30.
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.