What is agent-verification?

A self-checking guide for verifying changes in a toolkit repository before saying they are complete or ready. It requires running the relevant checks and reading their results.

Use it to run shell checks and smoke tests for scripts, inspect Markdown and configuration, and verify repository changes before reporting status.

It prevents unsupported claims that scripts pass, files are valid, or work is finished.

agent-verification — Skill by sflandergan

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/sflandergan/agentic-coding/agent-verification

Any agent

npx skills add sflandergan/agentic-coding --skill agent-verification

Clone the repo

git clone --depth 1 https://github.com/sflandergan/agentic-coding

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 671 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 2 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.

Model	Per session	Once invoked
Fable 5	$0.00025	$0.00671
Opus 5	$0.00013	$0.00336
Sonnet 5	$0.00005	$0.00134
Haiku 4.5	$0.00003	$0.00067

Measured yesterday against content hash 4e18a599ad97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

agent-verification scanned grade D with 2 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls -la .claude/skills/ # each should point to ../../.agents/skills/<name>

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .temp/smoke-test .temp/smoke-copy

.agents/skills/agent-verification/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Verification — Self-Maintenance

Core principle: Evidence before claims, always. If you haven't run the verification command, you cannot claim it passes.

The Gate

BEFORE claiming any status:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code
4. VERIFY: Does output confirm the claim?
5. ONLY THEN: Make the claim (with evidence)

Verification Commands

For bash scripts (`scripts/init.sh`, `scripts/copy.sh`)

shellcheck scripts/init.sh scripts/copy.sh
bash -n scripts/init.sh
bash -n scripts/copy.sh

Smoke run (scripts)

Run the script against a throwaway target dir under .temp/:

mkdir -p .temp/smoke-test
echo -e "1\n1\n.temp/smoke-test/target" | bash scripts/init.sh

For copy.sh:

mkdir -p .temp/smoke-copy && cd .temp/smoke-copy && git init && echo "placeholder" > README.md && git add . && git commit -m "init"
cd ../..
echo -e "1\n1" | bash scripts/copy.sh .temp/smoke-copy

Clean up after:

rm -rf .temp/smoke-test .temp/smoke-copy

For markdown files

No compilation check, but verify:

SKILL.md frontmatter has required name and description
Agent .md files have required description in frontmatter
Run codespell on changed markdown, agent, skill, README, and prose-heavy script files
No broken relative links (manual spot-check)

codespell README.md .agents/skills/agent-planning/SKILL.md

Scope codespell to changed files by default. Run it more broadly when a plan explicitly calls for repo-wide spelling validation.

Consistency checks

# README lists match actual files
ls .opencode/agents/          # should match README's agent list
ls .agents/skills/            # should match README's skill list

# Lockfiles match their distinct scopes
jq '.skills | keys' skills-lock.json
jq '.skills | keys' core/skills-lock.json

# Symlinks resolve
ls -la .claude/skills/        # each should point to ../../.agents/skills/<name>

Read the full file on GitHub · 102 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.

yesterday First seen · 102 lines · 25 tokens per session scan D 4e18a599ad97

Subscribe to this mod's changes

agent-verification is a skill published in the GitHub repository sflandergan/agentic-coding (2 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 671 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Testing

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

agent-verification