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.
git clone --depth 1 https://github.com/ankitkr3/compoundedWrote 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.
[](https://agentmods.dev/agents/ankitkr3/compounded/skill-verifier)<a href="https://agentmods.dev/agents/ankitkr3/compounded/skill-verifier"><img src="https://agentmods.dev/badge/agents/ankitkr3/compounded/skill-verifier/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ankitkr3/compounded/skill-verifier"><img src="https://agentmods.dev/badge/agents/ankitkr3/compounded/skill-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.00925 |
| Opus 5.5 | $0.00024 | $0.00370 |
| Sonnet 5.5 | $0.00012 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00093 |
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 1mo 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 — 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:
- The full text of a proposed
SKILL.mdfile - The verification hint authored alongside it
- A summary of the just-completed task: the user's prompt, the final state of changed files, and the last few tool calls
- The proposal's age in days
- 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
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.
- 1mo ago First seen · 70 lines · 61 tokens per session scan A 79be0cb6d025
skill-verifier is an agent published in the GitHub repository ankitkr3/compounded (5 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 925 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
reviewer
Defensive code reviewer for /magi:review-code --single (or as a fallback when MAGI degrades to one reviewer). Reads the diff and surrounding code, produces a structured Critical / Important / Note report. Read-only — does not edit files. Default model is Opus-class.
developer
TDD-first implementation worker dispatched by /magi:go. Receives a complete task brief (PLAN/SPEC excerpt, file context, interface contracts, conventions) and executes one task or one parallel lane. Writes code + tests; does not make architecture decisions; reports DONE / BLOCKED back to coordinator. Default model is…
review-agent
A code-review agent that examines a Git diff against architecture, API, security, and coding requirements, then writes a review report.
goal-contract-auditor
Audits the trust contract against the code. Invoke after changing anything the engine prints, adding a record field, or adding an agent — finds strings the engine says that the contract never declared.
skill-reviewer
Use this agent when the user has created or modified a skill and needs quality review, asks to "review my skill", "check skill quality", "improve skill description", or wants to ensure skill follows best practices. Trigger proactively after skill creation. Examples: Context: User just created a new skill user: "I've…
symfony-security-auditor
Read-only security audit of Symfony authentication and authorization: firewalls, accesscontrol, voters, API Platform security, rate limiting, CSRF, password hashing, and input validation. Use proactively after changes to security.yaml, voters, controllers, forms, or API resources.