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.
npx skills add ankitkr3/compounded --skill compounded-verifiergit 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/skills/ankitkr3/compounded/compounded-verifier)<a href="https://agentmods.dev/skills/ankitkr3/compounded/compounded-verifier"><img src="https://agentmods.dev/badge/skills/ankitkr3/compounded/compounded-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/skills/ankitkr3/compounded/compounded-verifier"><img src="https://agentmods.dev/badge/skills/ankitkr3/compounded/compounded-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 | $0.00067 | $0.01467 |
| Opus 5.5 | $0.00027 | $0.00587 |
| Sonnet 5.5 | $0.00013 | $0.00293 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
compounded-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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Verifier (compounded)
You are the verifier. A .proposed/ skill claims it solves a class of tasks. A real task in that class has just completed. Your job is to decide: would this skill, if applied to that task, have produced the right outcome?
Your decision is binary: PASS or FAIL. Both outcomes are recoverable. Both are logged.
Your inputs
You will receive:
- The full SKILL.md of the proposed skill
- The verification hint authored alongside it
- The final state of the just-completed task: file diffs, key tool calls, the user's original prompt, and the user's last message
- The proposal's age and any prior verification attempts
Two kinds of proposal
Check the frontmatter for a kind: field first:
- No
kind, orkind: procedure— a replayable procedure. Apply the procedure rubric below. kind: rule— a behavioral rule learned from a user correction. Apply the rule rubric (next section) INSTEAD of the procedure replay question. Rules have no numbered steps to replay; judging them on "would the procedure have reproduced the outcome" is a category error.
Rule rubric (kind: rule only)
Hard fails:
- Malformed frontmatter or missing required fields → FAIL,
malformed-frontmatter - The "rule" is a one-off bound to session-specific values (a literal path, port, repo, or person) with no generalizable trigger → FAIL,
not-abstracted - The trigger in
descriptionis so broad it would fire on every task ("whenever the user asks for anything") → FAIL,vague-procedure - Contradicts the user's CLAUDE.md or USER.md → FAIL,
conflicts-with-user-rules - Duplicates an existing skill → FAIL,
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, and the trigger is crisp → PASS
- Yes, but trigger could be tighter → PASS-with-notes
- Unsure → PASS-low-confidence (the trust gradient demotes rules that misfire)
- No, the rule misstates what the user actually wanted → FAIL,
outcome-mismatch
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 · 122 lines · 67 tokens per session scan A 6b95d6f62152
compounded-verifier is a skill published in the GitHub repository ankitkr3/compounded (5 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 1,467 once invoked, about $0.0003 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 skills, from other repositories
access
Manage who may drive telegram-topics sessions — view and edit the user allowlist. Use when the user asks to allow or remove a Telegram user, check who's allowed, or lock the channel down.
version-sentinel
Use when adding, bumping, or changing a dependency in package.json, requirements.txt, constraints.txt, pyproject.toml, Cargo.toml, .csproj, .fsproj, or .vbproj. Triggered automatically by version-sentinel's PreToolUse hook (where the host supports hooks) — this skill explains how to satisfy the block and record a…
personal-voice-capture
Use when a user wants an agent to learn, encode, or improve their personal writing voice as a reusable skill through source-text ingestion and iterative calibration edits.
ai-trend-tracker
Answers questions about AI/ML news, tool launches, research papers, and learning resources (free courses, certificates, YouTube channels, podcasts, newsletters, learning paths) by searching the live web first and returning a cited, dual-layer (ELI5 + technical + honest verdict) explanation tailored to the user's role…
ai-native-design
A workflow for turning a product brief and API contract into frontend design prompts and implementation guidance. It supports three outside design channels and keeps generated frontend work aligned with the same brief and contract.
backend-development
A set of instructions for building server-side code such as APIs and database-backed applications. It uses API contracts, data models, the chosen technology stack, and tests as the project’s reference points.