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 skills/bcanfield/agentic-tech-debt/initnpx skills add bcanfield/agentic-tech-debt --skill initgit clone --depth 1 https://github.com/bcanfield/agentic-tech-debtWhat 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 | $0.00074 | $0.01341 |
| Opus 5 | $0.00037 | $0.00671 |
| Sonnet 5 | $0.00015 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/debt-ops:init
Write or update a ## Tech debt operations section in ./CLAUDE.md. Idempotent — only the managed section changes.
1. Read the cached commands
TOPLEVEL=$(git rev-parse --show-toplevel)
REPO_HASH=$(printf '%s' "$TOPLEVEL" | shasum | cut -c1-12)
# Locate this repo's plugin cache. CLAUDE_PLUGIN_DATA is set in hook
# subprocesses but NOT in the skill's bash env, so glob the standard
# Claude Code plugin-data dirs and fall back to the legacy cache path.
CACHE_DIR=""
for D in \
${CLAUDE_PLUGIN_DATA:+"$CLAUDE_PLUGIN_DATA/cache/$REPO_HASH"} \
"$HOME/.claude/plugins/data"/debt-ops*/cache/"$REPO_HASH" \
"$HOME/.cache/debt-ops/cache/$REPO_HASH"; do
[ -d "$D" ] && { CACHE_DIR="$D"; break; }
done
LIST="$CACHE_DIR/feedback.list"
[ -n "$CACHE_DIR" ] && [ -f "$LIST" ] && cat "$LIST"
# Detected ADR/registry dirs (ADR 0006/0009). Fall back to the co-located
# defaults if the cache files aren't written yet.
ADR_DIR=$( [ -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 the file doesn't exist, the SessionStart discovery prompt hasn't run yet. Tell the developer:
No cached quality commands yet. Start a new session so I can detect them, then re-run /debt-ops:init.
…and stop.
2. Compose the section (template)
Substitute {{COMMANDS}} with the cache contents verbatim, {{ADR_DIR}} with the detected adr-dir, and {{REGISTRY_DIR}} with the detected registry-dir (from step 1).
## Tech debt operations
<!-- this section is auto-managed by the debt-ops Claude Code plugin; safe to edit, run /debt-ops:init to regenerate -->
### Disciplines
1. The test for debt: would a future reader ask "why this way?" If yes, register via `/debt-ops:add` immediately — no prompt. This is judgment, not a marker scan: a `TODO`/`FIXME`/`HACK`/`XXX` is the obvious case, but an unmade decision, a stub, a loosened type, or a default picked "for now" all count even with no marker in the diff. Use `payoff_trigger: unknown` if unsure. Announce: `+1 entry: <slug> (drop?)`. Over-register freely; the developer drops with "drop it".
2. When making an architecturally significant change — a data model, public interface, security boundary, release pipeline, or a dep-manifest change that is a major-version bump or a *new* top-level dependency — draft an ADR under `{{ADR_DIR}}/` in Nygard format: a `# NNNN — Title` heading, `**Date:**` and `**Status:**` lines, then Context, Decision, Consequences, Alternatives, Payoff trigger. Create the directory if needed. Only draft an ADR when there are two credible alternatives; if you cannot list two, it is a comment, not an ADR. An ADR with a payoff trigger *is* deliberate debt — when you write one, also call `/debt-ops:add` so the registry entry mirrors the ADR (don't conclude "no markers, no debt").
3. Read entries under `{{REGISTRY_DIR}}/` before changing files they reference.
### Quality commands
These run after every edit under a 3 s budget per command. Edit freely; the plugin reads tolerantly. Lines starting with `#` are estimates/comments and are skipped at run time.
<!-- debt-ops:feedback v1 -->
{{COMMANDS}}
<!-- /debt-ops:feedback -->
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.
- 2d ago First seen · 93 lines · 74 tokens per session scan A 31815dd0b012
init is a skill published in the GitHub repository bcanfield/agentic-tech-debt (8 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,341 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 skills, from other repositories
verify-pr
This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.
agent-reproduce-feature
Use when reproducing an existing Codex or Claude Code feature in Qwen Code or another agent CLI by choosing a reference agent, capturing HTTP request bodies, prompts, tool/function schemas, terminal output, and then implementing the matching behavior in the target repo.