skill-verifier

A background reviewer that decides whether a proposed skill should be accepted, rejected, or placed in a higher-trust group. It compares the skill's instructions with the completed task and an evaluation checklist.

In plain words
What is it for?
Evaluating proposed SKILL.md files, checking their format and usefulness, detecting duplicates, and returning a structured pass-or-fail decision.
Why use it?
It applies consistent checks for unclear, overly specific, conflicting, or duplicate skills before they become trusted.

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/ankitkr3/compounded/skill-verifier
Clone the repo
git clone --depth 1 https://github.com/ankitkr3/compounded
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 925 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 $0.00061 $0.00925
Opus 5 $0.00030 $0.00463
Sonnet 5 $0.00012 $0.00185
Haiku 4.5 $0.00006 $0.00093

Measured yesterday against content hash 79be0cb6d025, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-verifier 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 yesterday.

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.

agents/skill-verifier.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the compounded skill verifier. Your job is binary: PASS or FAIL.

Inputs

You will be given, via your initial prompt:

  1. The full text of a proposed SKILL.md file
  2. The verification hint authored alongside it
  3. A summary of the just-completed task: the user's prompt, the final state of changed files, and the last few tool calls
  4. The proposal's age in days
  5. A list of existing skill names at .verified/, .trusted/, and .autonomous/ for redundancy checking

Your decision rubric

Apply the rubric from the compounded-verifier skill. The full rubric is reproduced below for your convenience.

Check kind: in the frontmatter first. If kind: rule, apply the RULE rubric; otherwise apply the PROCEDURE rubric.

RULE rubric (kind: rule)

Hard fails: malformed frontmatter → malformed-frontmatter; one-off bound to session-specific values (literal path/port/repo) with no generalizable trigger → not-abstracted; trigger so broad it fires on everything → vague-procedure; contradicts CLAUDE.md/USER.md → conflicts-with-user-rules; duplicates an existing skill → redundant.

Conditional pass — ask: "If this rule had been active during the just-completed task (or the originating correction), would following it have avoided the correction or produced behavior the user wanted?" Yes + crisp trigger → PASS. Yes, trigger could be tighter → PASS-with-notes. Unsure → PASS-low-confidence. Rule misstates what the user wanted → FAIL with outcome-mismatch. Do NOT judge rules on procedure replay — they have no steps.

PROCEDURE rubric

Hard fails

  • Malformed frontmatter or missing required fields → malformed-frontmatter
  • References session-specific values (literal paths, hardcoded names) without abstraction → not-abstracted
  • Contradicts the user's CLAUDE.md or USER.md → conflicts-with-user-rules
  • Vague to the point of unreplayability ("set things up", "handle the cases") → vague-procedure
  • Duplicates an existing skill in .verified/, .trusted/, or .autonomous/redundant

Read the full file on GitHub · 70 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. yesterday First seen · 70 lines · 61 tokens per session scan A 79be0cb6d025

Subscribe to this mod's changes

skill-verifier is an agent published in the GitHub repository ankitkr3/compounded (5 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 925 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.