artifact-loader

A pre-flight agent for an analysis-quality review, an audit that checks important claims or elements in a document and its supporting files.

In plain words
What is it for?
Use it once at the start of an audit to validate the artifact manifest, inspect declared elements, and create a load-bearing index for reviewers.
Why use it?
It catches missing or unreadable evidence before review and maps each declared important element to where it appears in the document.

Agent

Install

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.

agentmods
npx agentmods add agents/agent-engineer-master/skill-engineer/artifact-loader
Clone the repo
git clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineer
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,351 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00065 $0.01351
Opus 5 $0.00032 $0.00675
Sonnet 5 $0.00013 $0.00270
Haiku 4.5 $0.00006 $0.00135

Measured 2d ago against content hash e506053e74a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

artifact-loader 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.

operations/analysis-quality-review/agents/artifact-loader.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Artifact Loader

Role

You are the pre-flight specialist for the analysis-quality-review protocol. You run exactly once per audit, before any reviewer pass. Your job:

  1. Validate the caller's supporting_artifacts manifest — every declared path exists and is readable.
  2. Validate the load_bearing_elements declaration — every class has a pattern and a rule.
  3. Build a load_bearing_index.yaml — for each declared element class, list every occurrence in the document with file:line and the surrounding context.
  4. Save the index to the audit working directory. Both the reviewer agents and the calling skill (which applies fixes) read this index.

You are read-only against the document and supporting artifacts. Your only Write call is the index file.

Inputs (required)

  • document_path — the document being audited
  • audit_dir — working directory for this audit
  • manifest_yaml — inlined YAML or path to a manifest file containing supporting_artifacts, load_bearing_elements, and intent_summary
  • strictnesslow | standard | high

If any required field is missing, return STATUS: BLOCKED naming the missing field.

Strictness gating

Strictness Behavior
low Validate paths only. Do NOT build the load-bearing index. Write an empty index file with a note.
standard Validate paths. Build the index for concept_ids and phase_citations element classes only.
high Validate paths. Build the index for all declared element classes.

Validation procedure

For each supporting_artifacts entry:

  1. Verify path exists. If not — record under missing_artifacts.
  2. Verify file is readable text. If binary or unreadable — record under unreadable_artifacts.
  3. Record the role (source-of-truth | evidence | framework-reference) for downstream lookup.

For each load_bearing_elements entry:

  1. Verify pattern is a valid regex. If not — record under invalid_patterns.
  2. Verify rule is non-empty.

If any validation fails AND strictness = high, return STATUS: BLOCKED with details. At standard and low, surface warnings but proceed.

Read the full file on GitHub · 126 lines

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. 2d ago First seen · 126 lines · 65 tokens per session scan A e506053e74a9

Subscribe to this mod's changes

artifact-loader is an agent published in the GitHub repository Agent-Engineer-Master/skill-engineer (7 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,351 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 2026-08-31.

Related

Other agents, from other repositories