infrastructure-sia

infrastructure-sia is a skill for Claude Code, Codex from docxology/template. It costs 53 tokens per session (414 once invoked), scanned A, original, Apache-2.0.

A testing harness for evaluating agents on tasks with separate public inputs, private answers, and a reference solution. SIA means Self-Improvement Agent and describes a loop where an agent produces work, receives evaluation, and improves.

In plain words
What is it for?
Use it to validate agent task folders, replay evaluation runs, and optionally run live generate-and-feedback loops in template projects.
Why use it?
It catches invalid task layouts and makes agent evaluations repeatable through saved fixture runs, while keeping evaluation-only data hidden from the agent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/pipeline/stage_02_analysis.py --project templates/template_sia.

Good fit Use it to validate agent task folders, replay evaluation runs, and optionally run live generate-and-feedback loops in template projects.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/docxology/template
agentmods
npx agentmods add skills/docxology/template/sia

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for infrastructure-sia

README.md
[![agentmods](https://agentmods.dev/badge/skills/docxology/template/sia.svg)](https://agentmods.dev/skills/docxology/template/sia)
Your own site
<a href="https://agentmods.dev/skills/docxology/template/sia"><img src="https://agentmods.dev/badge/skills/docxology/template/sia.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00414
Opus 5 $0.00026 $0.00207
Sonnet 5 $0.00011 $0.00083
Haiku 4.5 $0.00005 $0.00041

Measured 4d ago against content hash 9ba99a487356, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

infrastructure-sia 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 4d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (__init__.py, __main__.py, cli.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

infrastructure/sia/SKILL.md · 50 lines

What it actually says

SIA Harness

Deterministic harness for Meta → Target → Feedback generation loops with public/private task splits. Implements contracts inspired by hexo-ai/sia; does not vendor upstream code.

Commands

uv run python -m infrastructure.sia.cli validate projects/templates/template_sia/tasks/mini_classify
uv run python -m infrastructure.sia.cli inspect-run RUN_SUMMARY_JSON [--json]
uv run python scripts/pipeline/stage_02_analysis.py --project templates/template_sia

Public API

from infrastructure.sia import (
    RunConfig,
    TaskLayout,
    load_agent_execution,
    run_evaluation,
    run_sia_loop,
    validate_task_dir,
)

Task layout

Each task directory exposes:

  • data/public/ — agent-visible inputs
    • data/public/task.md — required task description (validate_task_dir hard-fails if absent)
    • data/public/evaluate.py — writes results.json with metric_name, metric_value, n_samples
  • data/private/ — evaluation-only labels
  • reference/ — baseline target agent (reference/reference_target_agent.py required)

Exemplar project

projects/templates/template_sia/ runs fixture replay by default (live=False). Pass --live-sia on scripts/run_sia_loop.py for opt-in Ollama-backed feedback (not CI) — the feedback note is illustrative, not applied; live mode performs no code mutation and uses no sandbox, so cross-generation improvement is shown only via fixtures.

Changes

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.

  1. 4d ago First seen · 50 lines · 53 tokens per session scan A 9ba99a487356

Subscribe to this mod's changes

infrastructure-sia is a skill published in the GitHub repository docxology/template (19 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 414 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.

Related

Other skills, from other repositories

launch-check

Run a pre-demo/pre-launch audit of the app - test data, broken screens, missing error states, brand consistency. Use when asked to 'demo check', 'launch check', 'pre-demo audit', 'check before user interview', 'audit before demo'.

craigcossairt/trellis · 55 tokens

cross-validation

The cross-validation skill enables the cross-validation agent to validate consistency between agent outputs and their sources. It provides the rules registry and validation runner that check pairwise consistency across the agent pipeline.

paruff/uFawkesAI · 2 tokens

lang-go

Go toolchain: golangci-lint, go vet, go test, go mod. CI gate commands, file layout, interface patterns. Use when working on a Go project.

paruff/uFawkesAI · 40 tokens

lang-python

Python toolchain: ruff, mypy, pytest, pytest-cov, uv/pip. CI gate commands, file layout, pyproject.toml config. Use when working on a Python project.

paruff/uFawkesAI · 44 tokens

live-system-verification

Stands up a real running instance of the affected component(s) and runs testtype:live-system acceptance criteria against it — real HTTP calls, real process behavior, real evidence. Not a mock, not a simulated environment. Use when tasks.json contains any acceptance criterion tagged testtype: live-system.

paruff/uFawkesAI · 65 tokens

performance-smoke-testing

Validate basic performance characteristics to detect regressions. Use when running lightweight load tests to measure latency, throughput, and error rates.

paruff/uFawkesAI · 30 tokens