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/metricsnpx skills add bcanfield/agentic-tech-debt --skill metricsgit 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/metrics)<a href="https://agentmods.dev/skills/bcanfield/agentic-tech-debt/metrics"><img src="https://agentmods.dev/badge/skills/bcanfield/agentic-tech-debt/metrics.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.00972 |
| Opus 5 | $0.00036 | $0.00486 |
| Sonnet 5 | $0.00014 | $0.00194 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
metrics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/debt-ops:metrics
Read the hidden metrics log and tell the user whether v1's tripwires are tripping.
1. Find the log
TOPLEVEL=$(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="$D"; break; }
done
LOG="$CACHE_DIR/metrics.jsonl"
if [ -n "$CACHE_DIR" ] && [ -f "$LOG" ]; then
tail -n 500 "$LOG"
else
echo "MISSING: no metrics.jsonl found for repo hash $REPO_HASH"
fi
If the file is missing or empty, tell the user the hooks haven't fired yet in this repo and stop.
2. The log format
One JSON object per line, three event shapes:
{"event":"edit","file":"...","registry_count":N,"ts":"..."}— every agent edit{"event":"feedback","file":"...","result":"pass|fail","ts":"..."}— every quality-check fire{"event":"session","registry_count":N,"adr_count":M,"ai_authored_count":K,"ts":"..."}— start of each session
Timestamps are ISO-8601 UTC.
3. Compute the tripwires
Filter to the last 7 days. Then compute:
- Edits / sessions — counts of
event:editandevent:session. - Registry growth — last
registry_countminus first (across either edit or session events). >0 means Discipline 1 is firing. - ADR growth — last
adr_countminus first (session events only). - AI-authored share trend — first vs. last session percentage (
ai_authored_count / registry_count, when registry_count>0). - Feedback pass rate —
count(result:pass) / count(event:feedback). - FAIL → PASS rate — for each feedback event with
result:fail, look at the next feedback event for the same file. Count those that flipped topass. Divide by total fails. Below 50% means Claude isn't reliably acting on hook output — the architectural alarm bell.
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.
- 5d ago First seen · 92 lines · 72 tokens per session scan A e801584fcc19
metrics is a skill published in the GitHub repository bcanfield/agentic-tech-debt (8 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 972 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
codex-thread-orchestration
Use when running Arcgentic V2 in Codex and the current thread must orchestrate fixed Planner, Developer, Test, and Auditor role threads.
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
arcgentic
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
audit-round
External-audit role for arcgentic rounds. Loaded when arcgentic state.yaml is in awaitingaudit or auditinprogress, OR when the user explicitly requests an external audit of a finished round, OR when reviewing a handoff doc + commit chain against the round's declared scope. Produces a PASS / NEEDSFIX / AUDITINCOMPLETE…
orchestrate-round
Main-session orchestrator for arcgentic rounds. Use when in single-session mode, when a project-level session mode must drive dispatch order, or when manually advancing the state machine. Dispatches role sub-agents, verifies structured outputs, and owns PASS-only close-round execution.
using-arcgentic
Entry skill for the arcgentic plugin — establishes the four-role workflow (planning / dev+self-audit / external-audit / reference-tracking), the round state machine, and when to switch roles or dispatch sub-agents. Use when starting any session in a project that has .agentic-rounds/state.yaml present, OR when the user…