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.
git clone --depth 1 https://github.com/paruff/uFawkesAIWrote 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/commands/paruff/ufawkesai/measure)<a href="https://agentmods.dev/commands/paruff/ufawkesai/measure"><img src="https://agentmods.dev/badge/commands/paruff/ufawkesai/measure/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/commands/paruff/ufawkesai/measure"><img src="https://agentmods.dev/badge/commands/paruff/ufawkesai/measure.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 | $0.00021 | $0.01472 |
| Opus 5.5 | $0.00008 | $0.00589 |
| Sonnet 5.5 | $0.00004 | $0.00294 |
| Haiku 4.5 | $0.00002 | $0.00147 |
Grade A, and why
measure 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- [ ] uFawkesObs is running: `curl -s http://localhost:9090/-/healthy` returns `OK` How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Measure
Invoke: Monthly schedule OR after a significant release OR when measure issue filed by release agent. DORA: AI Capability 2: Healthy data ecosystems + AI Capability 7: Quality internal platforms Token cost: Medium (queries external Prometheus/Loki endpoints) Output:
dora-snapshot-YYYY-MM.json+dora-snapshot-YYYY-MM.md
Purpose
Translate platform activity into DORA delivery metrics and ROI signal. Ensures that
AI-assisted velocity gains are visible at the organizational level — not absorbed by
"downstream disorder" (DORA ROI 2026). Feeds the learn skill when anomalies are
detected, and @planner when capability gaps are identified.
This agent runs on a schedule. It does not wait to be asked. It is a thin trigger:
the metric collection and ROI translation methodology live in the dora-measurement
and ROI-reporting skills — this file only defines when to run, what to check first,
what counts as an anomaly, and what to hand off.
Trigger Conditions
| Trigger | Frequency | Source |
|---|---|---|
| Monthly cadence | 1st of each month | Scheduled (cron or manual) |
| Post-release | After each GitHub Release | Filed by release agent (issue label: dora-measurement) |
| Anomaly investigation | Ad hoc | Filed by the learn skill or human observation |
Pre-conditions
- Load
dora-measurementskill:"load dora-measurement skill" - Load
ROI-reportingskill:"load roi-reporting skill" - uFawkesObs is running:
curl -s http://localhost:9090/-/healthyreturnsOK - Prometheus retention covers the measurement window (default: 30 days)
- Loki is running and log ingestion is current
-
GRAFANA_URL,PROMETHEUS_URL,LOKI_URLenvironment variables set - Previous snapshot exists for trend comparison (warn if not — first run)
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.
- 8d ago Changed 33e2119ac91e
- 10d ago Changed · +11 lines 506792da4ebe
- 14d ago First seen · 138 lines · 21 tokens per session scan A 389d53a4b982
measure is a command published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,472 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-28.
Other commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
plan-review
Compare an implementation plan against the current codebase.
help
Show all DeepInit commands + key options, grouped and ordered by how often you'll use them. Instant, no analysis.
harness-explain
Explain AI Harness Doctor instructions for one target path.
session-recap
Summarize recent CHANGELOG.md entries for context restoration. Parses the canonical heading shape ## YYYY-MM-DD — pass-N — summary. Filters: last N (default 10), YYYY-MM date prefix, or "today". Supports --json for machine-readable output.
undo
Undo last commit safely. Use for undo commit, revert, uncommit, cancel commit.