response-validation

response-validation is a skill for Claude Code, Codex from vladkesler/initrunner. It costs 24 tokens per session (440 once invoked), scanned A, original, Apache-2.0.

A check for whether an API response has the expected type, valid data, fields, and size. An API is a service that software calls to exchange data, often in JSON format.

In plain words
What is it for?
Use it to check API endpoints, detect changes in response structure, and investigate upstream data or service problems.
Why use it?
It catches responses that report success but contain missing fields, unexpected empty or null values, HTML error pages, or unusual amounts of data.

Skill for Claude CodeCodex

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 skills/vladkesler/initrunner/response-validation
Any agent
npx skills add vladkesler/initrunner --skill response-validation
Clone the repo
git clone --depth 1 https://github.com/vladkesler/initrunner

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 440 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00024 $0.00440
Opus 5 $0.00012 $0.00220
Sonnet 5 $0.00005 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 3d ago against content hash 6d0a859fb789, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

response-validation scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s --max-time 10 <URL>
examples/roles/api-monitor/skills/response-validation/SKILL.md · 73 lines

What it actually says

API response validation skill.

When to activate

  • When an endpoint returns 2xx but the response content looks unexpected (wrong content type, empty body, unusual size)
  • When the user asks to validate response format or schema

Check command

curl -s --max-time 10 <URL>

Capture the full response body for analysis.

Checks

1. Content-Type

Verify the response Content-Type matches what is expected. JSON APIs should return application/json. Use -i flag to see headers:

curl -s -i --max-time 10 <URL> | head -20

2. Valid JSON

If the endpoint is expected to return JSON, verify the body parses as valid JSON. Look for HTML error pages returned instead of JSON (common failure mode).

3. Expected fields

Compare the response structure against the last known structure stored in semantic memory (category: "response_schema"). Look for:

  • Missing top-level fields that were previously present
  • New unexpected top-level fields (informational, not an alert)

4. Null values

Check for null values in fields that were previously non-null. This can indicate upstream data pipeline failures.

5. Response size

Compare the response body size against the baseline from memory (category: "response_size"). Significant deviations (>50% smaller or >200% larger) may indicate issues.

MUST

  • Show actual vs expected values when reporting issues
  • Store the response structure in semantic memory (category: "response_schema") for future comparison
  • Store the response size baseline in semantic memory (category: "response_size")

MUST NOT

  • Alert on cosmetic differences (field ordering, extra whitespace)
  • Alert on additional optional fields being added
  • Flag response size changes for endpoints that return variable- length data (search results, paginated lists) without checking if the variance is normal
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. 3d ago First seen · 73 lines · 24 tokens per session scan A 6d0a859fb789

Subscribe to this mod's changes

response-validation is a skill published in the GitHub repository vladkesler/initrunner (41 stars, last pushed 5d ago), licensed Apache-2.0. It adds 24 tokens to every session and 440 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.