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 perniemann/pnCore --skill pn-discipline-philosophygit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-discipline-philosophy)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-discipline-philosophy"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-discipline-philosophy/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/perniemann/pncore/pn-discipline-philosophy"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-discipline-philosophy.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 | $0.00066 | $0.01613 |
| Opus 5 | $0.00033 | $0.00807 |
| Sonnet 5 | $0.00013 | $0.00323 |
| Haiku 4.5 | $0.00007 | $0.00161 |
Grade A, and why
pn-discipline-philosophy 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 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.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Discipline Philosophy
Purpose
Use this as a discipline rulebook for:
- Test-driven development (TDD)
- Systematic debugging and root cause analysis
- Implementation planning and work breakdown
- Code quality and verification
- Minimal, evidence-based change
It unifies how to work: test-first, confirm-before-fix, incremental, verifiable.
When to use
- Implementing features or fixes (TDD workflow)
- Debugging failures with unclear cause
- Planning multi-step implementation
- Establishing team or AI agent discipline
- Reviewing for guess-and-patch, untested changes, or scope creep
For workflow, audit checklist, and templates, see reference.md.
Core Philosophy (non-negotiables)
Test before production code
Do not write production code before a failing test. If production code exists without a failing test, remove it and write the failing test first. Red–Green–Refactor: smallest failing test, minimal code to pass, then refactor.
Root cause before fix
Reproduce → Isolate → Hypothesize → Confirm. Do not guess-and-patch. One hypothesis at a time; confirm or reject before the next. Fix only after root cause is confirmed.
Minimal change
Smallest change that fixes the problem. Prefer targeted fixes over broad edits. Refactor only after tests pass. No "while I'm here" scope expansion without a new test.
Measure before optimize
No performance work without a recorded baseline. State the metric (LCP, INP, query ms, allocation count), the measured current value, and the target. Optimization without numbers is decoration. Profile → identify hot path → change → re-measure. Reject "should be faster" — show the delta.
Goodhart's Law caveat. Once a metric becomes a target (a KPI, a budget cap, a "must hit"), it stops being a measure of the underlying property — it measures only itself. Token usage, test count, lighthouse score, "skills loaded" — useful as feedback, dangerous as goals. When citing a metric, state whether it is feedback or target; never optimize a target without also tracking the property it was meant to proxy.
What ships with it
2 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.
- 8d ago First seen · 189 lines · 66 tokens per session scan A fc55e86b5123
pn-discipline-philosophy is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 5d ago), licensed MIT. It adds 66 tokens to every session and 1,613 once invoked, about $0.0003 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
diagnose-hard-problem
Disciplined diagnosis loop for hard problems, diagnosing bugs and regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.
taiyi-dev
A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.