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/jyt6640/persona-harness/programmingnpx skills add jyt6640/persona-harness --skill programminggit clone --depth 1 https://github.com/jyt6640/persona-harnessWrote 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/jyt6640/persona-harness/programming)<a href="https://agentmods.dev/skills/jyt6640/persona-harness/programming"><img src="https://agentmods.dev/badge/skills/jyt6640/persona-harness/programming.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 | $0.00025 | $0.00270 |
| Opus 5 | $0.00013 | $0.00135 |
| Sonnet 5 | $0.00005 | $0.00054 |
| Haiku 4.5 | $0.00003 | $0.00027 |
Grade A, and why
ph-programming 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 today.
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.
What it actually says
(PH) Programming Discipline
This adapter exposes the canonical Persona Harness skill to this host only. Discovery alone does not authorize workflow, shell, network, GitHub, authority, evidence, or external actions.
Programming Discipline
Use this concise, Persona-owned guidance only after the user has selected a scoped behavior. Read the project profile and nearby code first, write a failing focused test, make the smallest compatible change, then verify the changed behavior. Do not infer a project stack from this package's Node metadata and do not start a workflow, branch, ticket, or agent automatically.
The packaged language overlay is references/java/ for Java/Spring projects.
Other language references are not a packaged Persona contract and must not be
claimed as available guidance.
What ships with it
47 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.
- fixtures/java/no-excuse/fail/broad-catch/BroadCatchCase.java 228 B
- fixtures/java/no-excuse/fail/domain-framework-import/src/main/java/sample/member/domain/DomainFrameworkImportCase.java 115 B
- fixtures/java/no-excuse/fail/domain-framework-import/src/main/java/sample/member/domain/JpaImportCase.java 91 B
- fixtures/java/no-excuse/fail/domain-record/src/main/java/sample/member/domain/DomainRecordCase.java 72 B
- fixtures/java/no-excuse/fail/empty-catch/EmptyCatchCase.java 183 B
- fixtures/java/no-excuse/fail/field-injection/FieldInjectionCase.java 160 B
- fixtures/java/no-excuse/fail/mutable-static/MutableStaticCase.java 79 B
- fixtures/java/no-excuse/fail/optional-get/OptionalGetCase.java 164 B
- fixtures/java/no-excuse/fail/optional-get/OptionalLocalCase.java 193 B
- fixtures/java/no-excuse/fail/printf-debug/PrintfDebugCase.java 109 B
- fixtures/java/no-excuse/fail/printstacktrace/PrintStackTraceCase.java 116 B
- fixtures/java/no-excuse/fail/public-field/PublicFieldCase.java 71 B
- fixtures/java/no-excuse/fail/raw-runtime-throw/RawRuntimeThrowCase.java 117 B
- fixtures/java/no-excuse/fail/raw-type/RawMapCase.java 89 B
- fixtures/java/no-excuse/fail/raw-type/RawOptionalCase.java 103 B
- fixtures/java/no-excuse/fail/raw-type/RawTypeCase.java 91 B
- fixtures/java/no-excuse/fail/setter/src/main/java/sample/member/domain/SetterCase.java 149 B
- fixtures/java/no-excuse/fail/test-name-convention/AnotherBadTest.java 143 B
- fixtures/java/no-excuse/fail/test-name-convention/BadTest.java 128 B
- fixtures/java/no-excuse/fail/todo-no-owner/TodoNoOwnerCase.java 135 B
- fixtures/java/no-excuse/fail/vague-name/BadManager.java 42 B
- fixtures/java/no-excuse/pass/CleanDomain.java 445 B
- fixtures/java/no-excuse/pass/CleanTest.java 163 B
- fixtures/java/no-excuse/pass/MainPrinter.java 128 B
- references/java/anti-patterns.md 4.7 KB
- references/java/application-layer.md 8.9 KB
- references/java/architecture.md 5.8 KB
- references/java/backend.md 11 KB
- references/java/code-quality-refactoring.md 5.0 KB
- references/java/concurrency-discipline.md 3.2 KB
- references/java/domain-model.md 8.1 KB
- references/java/error-handling.md 8.2 KB
- references/java/foundations.md 2.8 KB
- references/java/java-idioms.md 4.9 KB
- references/java/language-core.md 5.4 KB
- references/java/method-and-naming.md 4.1 KB
- references/java/object-collaboration.md 5.0 KB
- references/java/performance-discipline.md 4.6 KB
- references/java/README.md 13 KB
- references/java/repository-pattern.md 7.9 KB
- references/java/technology-seams.md 13 KB
- references/java/test-design.md 5.0 KB
- references/java/testing.md 8.9 KB
- scripts/java/check-no-excuse-rules.sh 9.0 KB runs code
- scripts/java/new-project.py 21 KB runs code
- scripts/java/verify-no-excuse-fixtures.sh 798 B runs code
- scripts/java/verify-realish-samples.sh 3.3 KB runs code
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.
- today Changed · +9 lines · +4 tokens per session c800920df5cb
- 4d ago First seen · 20 lines · 21 tokens per session scan A 8b8a6d0a57e8
ph-programming is a skill published in the GitHub repository jyt6640/persona-harness (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 270 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
cmux-architecture
Skill "cmux-architecture" from manaflow-ai/cmux, covering cmux architecture, package architecture, layers, file organization and documentation.
fallback-and-resilience
What to do when a tool fails, an API hits a rate limit, or a site blocks scraping. Maps every primary tool to its best fallback so a single failure doesn't block the search.
cmux
End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash). Use when automation needs deterministic placement and navigation in a multi-pane cmux layout.