agentmods.dev

verify

A command for manually checking a proposed coding-agent skill before it is used automatically. It reads the proposal and a verification note, then asks a verifier to judge the skill against existing active skills.

In plain words
What is it for?
Use it with a proposed skill name to confirm that the proposal exists, run its verification, and apply the resulting approval or rejection.
Why use it?
It provides an early quality check and can reject a proposal or move it into an approved collection. The input does not specify the verifier’s exact evaluation criteria.

Command

5 2mo ago A scan 44 tokens original MIT
View the source file ankitkr3/compounded
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 commands/ankitkr3/compounded/verify
Clone the repo
git clone --depth 1 https://github.com/ankitkr3/compounded
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 356 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 $0.00044 $0.00356
Opus 5 $0.00022 $0.00178
Sonnet 5 $0.00009 $0.00071
Haiku 4.5 $0.00004 $0.00036

Measured yesterday against content hash 480df2608984, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify 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.

commands/verify.md · 27 lines

What it actually says

Manually verify a proposed skill named $ARGUMENTS.

Steps:

  1. Confirm the skill exists in .proposed/:

    !ls ~/.claude/compounded/skills/.proposed/$ARGUMENTS/SKILL.md 2>/dev/null && echo "found" || echo "not found"

  2. If it exists, read the proposed SKILL.md and the verification hint:

    • SKILL.md: ~/.claude/compounded/skills/.proposed/$ARGUMENTS/SKILL.md
    • Hint: ~/.claude/compounded/skills/.proposed/$ARGUMENTS/.verification_hint

  3. Use the skill-verifier subagent to evaluate the proposal. Pass it the SKILL.md content, the hint, a summary of any recent task that the user identifies as relevant, and the list of existing active skills (.verified/, .trusted/, .autonomous/).

  4. The subagent returns a JSON verdict. Apply it via:

    !python3 ${CLAUDE_PLUGIN_ROOT}/scripts/finalize_verification.py --name $ARGUMENTS --verdict-json '<paste-json-here>'

  5. Report the result to the user (graduated to .verified or rejected with reason).

If $ARGUMENTS is empty, ask the user which proposed skill to verify, then list the available proposals via ls ~/.claude/compounded/skills/.proposed/.

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 · 27 lines · 44 tokens per session scan A 480df2608984

Subscribe to this mod's changes

verify is a command published in the GitHub repository ankitkr3/compounded (5 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 356 once invoked, about $0.0002 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.

Building agentsMemory and contextPlanningagent-toolsai-agentsanthropicclaude-codeclaude-code-pluginclaude-plugin
Related

Other commands, from other repositories

cpp-init

Initialize C/C++ project-specific harness files (.clang-format, .clang-tidy, sanitizer build, init.sh tuned per build system). Run AFTER /anchor.

Redtropig/harness-anchor · 32 tokens

fieldtheory

Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…

afar1/fieldtheory-cli · 88 tokens

verify

Adversarial spec-vs-implementation verification for a completed task. Dispatches the spec-mentor subagent with fresh context (no anchoring bias), parses its verdict (PASS / DRIFT / NEEDS-MARTY), and updates the verification queue. The v7.4.0 architectural replacement for a dedicated "mentor session.".

MartyBonacci/specswarm · 68 tokens

add-agent

引导新增一个 Agent 适配器。用法 /add-agent.

shirenchuang/agentbro · 19 tokens

brand-setup

Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.

indranilbanerjee/socialforge · 20 tokens

save

Save this conversation as a new or existing reusable context.

XTSoftwareLabs/neatcontext-plugins · 10 tokens