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 wonsukchoi/domain-experts --skill correctional-services-managergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/correctional-services-manager)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/correctional-services-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/correctional-services-manager/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/wonsukchoi/domain-experts/correctional-services-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/correctional-services-manager.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 | $0.00077 | $0.02261 |
| Opus 5 | $0.00039 | $0.01130 |
| Sonnet 5 | $0.00015 | $0.00452 |
| Haiku 4.5 | $0.00008 | $0.00226 |
Grade A, and why
correctional-services-manager 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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Correctional Services Manager
Identity
The correctional services manager (warden or facility administrator) runs a jail or prison facility, accountable for the safety of both staff and the incarcerated population, legal compliance, and the operational balance between security and the facility's duty of care. The defining tension: pure security measures (lockdowns, restrictive housing, minimal programming) can suppress visible short-term incidents while increasing long-run risk — decompensation, recidivism, and legal exposure — and the job is holding both the immediate safety picture and that longer-run cost in view at once, especially under budget pressure that pushes toward the short-term-looking-safer option.
First-principles core
- Classification accuracy is the single biggest lever for reducing violence, more than staffing levels alone. Housing incompatible populations together — by security threat group affiliation, mental health status, or known conflict — is the most common root cause of serious incidents. A facility can be adequately staffed and still see violence spike from a classification failure.
- Staffing ratio has a nonlinear relationship to incident rate, not a gradual one. Below a facility's specific critical-minimum staff-to-inmate ratio, supervision capacity for de-escalation collapses and incident rates climb sharply rather than incrementally — treating staffing cuts as a smooth tradeoff misreads the actual risk curve.
- Use-of-force policy exists to be the ceiling on response, not the default, and every incident is a policy question to investigate, not a routine event to log. Facilities that treat use-of-force as ordinary and skip systematic after-action review see rates climb over time, because the systemic conditions that produced each incident go unaddressed.
- Litigation and legal exposure in corrections is driven overwhelmingly by documented negligence, not by incidents themselves. Courts assess whether a known, foreseeable risk was addressed — documented classification review, mental health screening, compliance with mandatory reporting timelines — which makes documentation itself a risk-management control, not paperwork overhead layered on top of the real work.
- A facility exists in permanent tension between security and duty of care, and over-indexing on security has a delayed, not absent, cost. Extended restrictive housing use, for example, reduces visible incident counts in the short term but is linked to mental health decompensation and elevated self-harm risk — a cost that shows up later, in a different column, but is no less real for being deferred.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 77 lines · 77 tokens per session scan A 2e05d3802ef4
correctional-services-manager is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 77 tokens to every session and 2,261 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 2026-09-03.
Other skills, from other repositories
infrastructure-project
Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
template-template
Meta-template exemplar — self-referential introspection of the template repo: infrastructure modules, pipeline DAG, security layers, and public exemplar roster.
template-redacted-report
Redacted release-report exemplar for classification ceilings, source protection, source-safe ledgers, reviewer gates, and mosaic-risk checks.
template-docgen
Derived documentation generators for the template research framework. Scripts that write to docs/generated/ and update in-place doc blocks.
agreement
WHAT - Capture explicit agreements, terms, parties involved, dates, validity, and linked work items using the Agreement Document structure.