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/markusneusinger/cite-citadel/open-prnpx skills add MarkusNeusinger/cite-citadel --skill open-prgit clone --depth 1 https://github.com/MarkusNeusinger/cite-citadelWrote 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/markusneusinger/cite-citadel/open-pr)<a href="https://agentmods.dev/skills/markusneusinger/cite-citadel/open-pr"><img src="https://agentmods.dev/badge/skills/markusneusinger/cite-citadel/open-pr.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 | $0.00130 | $0.01977 |
| Opus 5 | $0.00065 | $0.00988 |
| Sonnet 5 | $0.00026 | $0.00395 |
| Haiku 4.5 | $0.00013 | $0.00198 |
Grade A, and why
open-pr 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 4d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open a PR
The one path from "the change is done" to "a green PR waiting on the human". Gate locally first,
then push once. Every step below is runnable bash with an Expected: baseline so the first line
that does not match names what broke. You never merge — you stop at green + resolved and hand the
URL back.
0. Preconditions
- Work from the repo checkout on a feature branch (never commit to
main). ghis authenticated (gh auth status) anduv synchas been run.- Know the one-line topic of the change — it becomes the branch slug and the PR title.
1. Branch off main
Branch name is claude/<topic>-<slug> (kebab-case, no spaces). If you are already on such a branch
with your work, skip the checkout.
git fetch origin
git checkout -b claude/doctor-billing-warning origin/main # <topic>-<slug>, based on fresh main
Expected: Switched to a new branch 'claude/doctor-billing-warning'.
2. Route the diff (verify-corpus BEFORE the gates)
Look at what the diff touches — git diff --name-only origin/main...HEAD — and run the matching
corpus verification before the local gates, because the offline suite does NOT exercise a real
ingest:
| The diff touches… | Run first |
|---|---|
citadel/ingest.py, citadel/llm.py, or citadel/rules/** |
/verify-corpus <affected-corpus> — minimally the corpus that stresses the change (see the table in that skill); all for a broad rules/ingest change |
| anything else (cli, store, viewer, docs, tests) | nothing extra — the offline suite covers it |
verify-corpus spends a real ingest (minutes, your subscription), so scope it to the affected corpus,
not all, unless the change is broad. A hard-gate failure there is a finding — fix it before pushing.
Expected: verify-corpus ends with a per-corpus PASS verdict (its hard gates hold).
3. Local gates (all four must pass)
Run them one at a time so a red one stops you immediately. Do not pipe pytest through tail
inside an && chain — the pipe swallows pytest's exit code and a failing run looks green.
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.
- 4d ago First seen · 182 lines · 130 tokens per session scan A fc1b445c2c8a
open-pr is a skill published in the GitHub repository MarkusNeusinger/cite-citadel (2 stars, last pushed 6d ago), licensed MIT. It adds 130 tokens to every session and 1,977 once invoked, about $0.0006 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
design-debt-audit
Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).
design-impact-reporting
Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
survey-design
Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).
localization-design
Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).
motion-system
Define motion tokens — durations, easing vocabulary, and reduced-motion handling — for consistency product-wide. Use when standardising motion across a system. For crafting one specific animation, use animation-principles (interaction-design).