Borrowing it
Nothing to install: this file belongs to fabioc-aloha/Alex_Skill_Mall. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fabioc-aloha/Alex_Skill_Mall/main/.github/instructions/no-deferred-debt.instructions.mdgit clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_MallWrote 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/instructions/fabioc-aloha/alex_skill_mall/no-deferred-debt)<a href="https://agentmods.dev/instructions/fabioc-aloha/alex_skill_mall/no-deferred-debt"><img src="https://agentmods.dev/badge/instructions/fabioc-aloha/alex_skill_mall/no-deferred-debt/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/instructions/fabioc-aloha/alex_skill_mall/no-deferred-debt"><img src="https://agentmods.dev/badge/instructions/fabioc-aloha/alex_skill_mall/no-deferred-debt.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 | $0.00901 | $0.00901 |
| Opus 5 | $0.00451 | $0.00451 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
Alex_Skill_Mall no-deferred-debt.instructions.md 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 10d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
No Deferred Debt
Always-on rationale: debt surfaces in any context (script run, doc audit, file edit, command output). The "fix in same turn" discipline must fire whenever debt is observed, not only when working on specific file types. A scoped glob would create the failure mode it's designed to prevent.
If a turn surfaces tech debt — stale references, dead links, outdated content, dead-letter prompts, hardcoded names that no longer exist — fix it in the same turn. Do not log it as "non-blocking" or "follow-up workstream." The cheapest moment to fix the debt is the moment it surfaced.
Rule
When any of the following appears in a turn's output:
- A
grep/Select-Stringsurfaces references to artifacts I just deleted - A regen reveals stale counts in a manifest
- A file lookup returns a path that no longer exists
- A doc enumerates skills/instructions/prompts that are gone
- A script hardcodes names I just renamed or removed
- A link in a markdown file points to something that 404s locally
- A
descriptionorapplyToreferences concepts no longer in the brain
Fix it before declaring the turn done. Do not write "non-blocking, deferred to next pass" unless the debt is genuinely architectural and requires its own decision cycle (in which case open an explicit decision artifact — ADR draft, proposal, or HANDOFF entry naming the specific decision the deferral is waiting on).
"I'll fix it in the next session" is not an acceptable reason. The context is already loaded. The diff is already small. The reviewer is already in the file.
When deferral IS legitimate
| Deferral reason | Acceptable? |
|---|---|
| "Not in scope of this turn" | No — if I spotted it, it's in scope now |
| "Needs user decision" | Yes — but write the specific question in HANDOFF.md or a proposal, don't just leave the debt |
| "Requires architectural redesign" | Yes — open ADR draft naming the question, don't leave a silent broken state |
| "Would take more than 10 minutes" | Borderline — if it's mechanical, do it; if genuinely complex, name the deferral concretely with timeline |
| "Documentation update only" | No — docs that lie are debt |
| "Test data" | No — test data with dead refs makes tests untrustworthy |
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.
- 10d ago First seen · 57 lines · 901 tokens per session scan A c269e8c56d1b
Alex_Skill_Mall no-deferred-debt.instructions.md is an instructions file published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed 3d ago), licensed MIT. It adds 901 tokens to every session, about $0.0045 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.