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/aethrox/doctrine/prototypenpx skills add aethrox/doctrine --skill prototypegit clone --depth 1 https://github.com/aethrox/doctrineWhat 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 | $0.00059 | $0.01054 |
| Opus 5 | $0.00030 | $0.00527 |
| Sonnet 5 | $0.00012 | $0.00211 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
prototype 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype
A spike solution (Kent Beck and Ward Cunningham's term from Extreme Programming) is a quick, throwaway program written to answer one specific technical question, ignoring every other concern. The code is not the deliverable; the answer is. Most spikes aren't good enough to keep, and that's by design: keeping one is a sign it wasn't actually a spike.
Phase 1: Name the question
Before writing anything, state the single question this spike exists to answer; "does this state machine handle the cancel-mid-submit case correctly?", "can this API return the shape we need without an extra round-trip?", "what should this settings panel look like?" A spike with more than one question attached is really two spikes; split it.
Identify which kind of question it is, since it decides the artifact:
- "Does this logic / state model hold up?" → build a single shareable file (or minimal script) that drives the logic through the cases that are hard to reason about on paper, printing the resulting state after each step so the answer is visible, not inferred.
- "What should this look like / feel like?" → build the UI variation(s) directly in the app's existing routing/component conventions, switchable without rebuilding, so it can be looked at rather than described.
- "Will this technical approach even work?" → build the smallest possible harness that exercises the risky part end-to-end (the actual API call, the actual library, the actual integration point) and nothing else.
If the question is genuinely ambiguous and the user isn't reachable, default to whichever reading matches the surrounding code, and say so at the top of the spike rather than guessing silently.
Phase 2: Timebox it
A spike is a thin, deep drive at one unknown (the "spike through a log" the name comes from), not a general exploration. Set an explicit bound before starting (Beck's own spikes ran half a day to two days; cap at what the question actually needs) and stop when the question is answered, even if the code is ugly. A spike that's still running past its bound has usually stopped being a spike and turned into unplanned production work; surface that instead of continuing silently.
What ships with it
1 file 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.
- 2d ago First seen · 50 lines · 59 tokens per session scan A 09aa52a37e24
prototype is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 20d ago), licensed MIT. It adds 59 tokens to every session and 1,054 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 2026-08-30.
Other skills, from other repositories
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
release-openspec
Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is…
openspec-update-change
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.