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/saski/arnesto/alignnpx skills add saski/arnesto --skill aligngit clone --depth 1 https://github.com/saski/arnestoWhat 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 | $0.00033 | $0.00451 |
| Opus 5 | $0.00016 | $0.00226 |
| Sonnet 5 | $0.00007 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
align 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STARTER_CHARACTER = 🎯
Core Principle
Propose, don't ask. Think first, then present your thinking for confirmation. The user's job is to course-correct, not to generate the approach.
Flow
Read input → Think internally → Present chunk → Confirm → Next chunk
↑ |
└── Redirect ┘
- Read the input context
- Think through the full approach internally
- Present a rough outline of chunks coming — gives the user the full scope before drilling in
- Present each chunk progressively, starting from the highest level of abstraction
- Confirm each chunk with AskUserQuestion before moving to the next
- Drill down only after the big picture is confirmed
Presenting Chunks
Each chunk is a coherent topic. Present it with:
- ⭐ Recommended approach with brief rationale
- ❌ Alternatives considered with why they were rejected
- ASCII diagram when showing structure or flow
Grouping Decisions
Group related small decisions into a single chunk with ⭐/❌ for each choice within it.
Anti-example: Presenting framework choice, state management choice, and styling choice as three separate confirmation rounds — these are all "Tech Stack" and belong in one chunk.
Non-trivial decisions with major downstream implications get their own chunk.
Chunk Size
Scannable in one read. If it needs scrolling, split it.
Handling Redirects
When the user rejects a chunk, downstream design may change. Don't present pre-computed chunks that depend on the rejected one. Rethink from the redirect point forward.
Anti-patterns
- Asking open-ended questions instead of proposing (the user invoked this to see YOUR thinking)
- Presenting the entire design at once (defeats progressive confirmation)
- Moving to the next chunk without explicit confirmation
- Presenting trivial decisions one at a time
- Skipping ASCII diagrams for structural or flow topics
- Continuing with pre-planned chunks after a redirect without reconsidering
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 · 59 lines · 33 tokens per session scan A 77f8e7d229f9
align is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 7d ago), licensed Unlicense. It adds 33 tokens to every session and 451 once invoked, about $0.0002 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
pixir-delegate
Use Pixir as a headless subagent runtime from Claude Code or any harness with skill ! preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (pixir --json), parallel fan-out to N children (pixir delegate --spec), resumable steering (pixir resume), evidence…
pixir-delegate-codex
Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution…
pixir-diagnostics
Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
pixir-delegate-native
Delegate work to subagents from INSIDE a Pixir session using the native Subagent tools (spawnagent, waitagent, closeagent, listagents, sendinput) instead of shelling out to the pixir CLI. Use when you are a Pixir session that needs to fan out parallel workers, steer a child, or run skill-backed workflow templates …
repo-contracts-and-boundaries
Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.