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 bcanfield/agentic-tech-debt --skill debt-ops-initgit clone --depth 1 https://github.com/bcanfield/agentic-tech-debtWrote 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/bcanfield/agentic-tech-debt/debt-ops-init)<a href="https://agentmods.dev/skills/bcanfield/agentic-tech-debt/debt-ops-init"><img src="https://agentmods.dev/badge/skills/bcanfield/agentic-tech-debt/debt-ops-init/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/bcanfield/agentic-tech-debt/debt-ops-init"><img src="https://agentmods.dev/badge/skills/bcanfield/agentic-tech-debt/debt-ops-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 58 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00076 | $0.01471 |
| Opus 5.5 | $0.00030 | $0.00588 |
| Sonnet 5.5 | $0.00015 | $0.00294 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
debt-ops-init scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
REPO_HASH=$(python3 -c "import hashlib,subprocess;t=subprocess.run(['git','rev-parse','--show-toplevel'],capture_output=True,text=True).stdout.strip();print(hashlib.sha1(t.encode()).hexdigest()[:12] if t else '')") How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
debt-ops-init
Write or update a ## Tech debt operations section in the project's agent charter.
Idempotent — only the managed section changes.
Run only on explicit user request ("set up debt-ops", "init debt-ops", "write the disciplines"). Do not invoke this as part of normal work. (Tools with a debt-ops hook adapter inject these disciplines per-session automatically; this skill is the persistence step for everyone else.)
Why this matters more on skills-only tools
Without a hook adapter there is no per-edit enforcement and no automatic capture. The charter is the only place the disciplines live, so the agent self-applies them. That's "vibes," not a tripwire — be honest with the user that the persistent charter is the substitute for, not the equal of, the hook-driven write-time loop.
1. Pick the charter file
Use AGENTS.md at the repo root — the cross-tool charter most agents read. If the
project clearly standardizes on a different file your agent auto-loads
(GEMINI.md, .github/copilot-instructions.md, CLAUDE.md), use that instead and
tell the user which you picked.
2. Read any cached quality commands (optional)
If a hook adapter previously ran in this repo, it cached the project's quality commands. Include them if present; otherwise leave the placeholder.
REPO_HASH=$(python3 -c "import hashlib,subprocess;t=subprocess.run(['git','rev-parse','--show-toplevel'],capture_output=True,text=True).stdout.strip();print(hashlib.sha1(t.encode()).hexdigest()[:12] if t else '')")
CACHE_DIR="${DEBT_OPS_CACHE:-$HOME/.cache/debt-ops}/cache/$REPO_HASH"
[ -f "$CACHE_DIR/feedback.list" ] && cat "$CACHE_DIR/feedback.list"
ADR_DIR=$( [ -s "$CACHE_DIR/adr-dir" ] && cat "$CACHE_DIR/adr-dir" || echo "docs/adr" )
REGISTRY_DIR=$( [ -s "$CACHE_DIR/registry-dir" ] && cat "$CACHE_DIR/registry-dir" || echo "docs/debt" )
echo "adr-dir: $ADR_DIR"
echo "registry-dir: $REGISTRY_DIR"
If no commands are cached, detect the project's lint/type/test commands by scanning
its manifests (package.json, pyproject.toml, Cargo.toml, go.mod, Makefile,
…). Prefer commands that take a changed-file argument and run in a few seconds.
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.
- 1mo ago First seen · 107 lines · 76 tokens per session scan A b06f99b302a6
debt-ops-init is a skill published in the GitHub repository bcanfield/agentic-tech-debt (8 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,471 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
connect
Install the scoped Antigravity permission hook.
scout-ask
Use when the working directory is a Scout vault (it has knowledge-base/ and action-items/) and the user asks about the state of a project, initiative, person, decision, meeting or open thread ("where are we on X", "what's going on with Y", "who is Z", "what's on my plate"), or what Scout knows about a topic. Do not…
review
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.
brainstorm
Explores a codebase, researches the problem space, and produces an approved design specification before any code is written. Use when the user wants to create a new feature, add significant functionality, redesign a subsystem, or build something that touches multiple parts of the project.
seo-fix
Apply fixes from seo-audit findings. Reads audit JSON, classifies fixes by safety tier (SAFE/MODERATE/DANGEROUS), applies templates per framework. Supports Astro, Next.js, Hugo. Modes: default (SAFE only), --auto (SAFE+MODERATE), --all (all tiers, requires confirmation), --dry-run, --finding F1,F3, --fix-type…
a11y-audit
Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…