Agent skill

Verification Before Completion

by duckbugio in duckbugio/flock

Has the agent build, test and lint a change, re-read the request and check for regressions before it says a coding task is done, then report exactly what it ran.

MITAuto-check passedAgent Workflows

Install Verification Before Completion

skills CLI
$ npx skills add duckbugio/flock --skill verification-before-completion -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install duckbugio/flock verification-before-completion --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/duckbugio/flock.git skills-src && mkdir -p .claude/skills && cp -r skills-src/core/skills/verification-before-completion .claude/skills/verification-before-completion && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
verification-before-completion
GitHub stars
502
Token cost
~432 tokens
SKILL.md length
241 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Has the agent build, test and lint a change, re-read the request and check for regressions before it says a coding task is done, then report exactly what it ran.

  • Works in 5 steps: Build / compile what you changed. If it… → Run the relevant tests with the… → Run the linter/formatter the project… → …
  • About to tell the user a bug fix or feature is finished
  • SKILL.md covers Checklist (do it, don't… and Reporting
  • Calls go and npm

What it does

Before the agent reports a coding task as finished, fixed or working, this skill makes it gather evidence. The checklist covers building what changed, running the project's own test command (the narrowest command covering the change first, then the fuller suite if that is cheap), and running the project's linter or formatter. Where the changed area has no test and the change is not trivial, the agent adds one.

It also asks the agent to re-read the original request and confirm that every part is addressed, including edge cases and error paths, and to look for broken callers, contracts or neighbouring features. The final report has to name the commands that were run and their results rather than say 'should work', and any failure or unverified part must be stated plainly. A failing test is fixed before the task is called done.

When your agent uses it

  • About to tell the user a bug fix or feature is finished
  • Wrapping up a change that touched several files or callers
  • Before opening a pull request for a change the agent wrote

Example prompts

  • “Fix the null pointer in the order handler, and don't say it's done until you've verified it.”
  • “Before you wrap up, run the tests and the linter and tell me exactly what passed.”
  • “Double-check that the new pagination change didn't break any callers.”

Requirements

  • A project with build, test or lint commands the agent can run

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Build / compile what you changed. If it doesn't build, it isn't done.
  2. Run the relevant tests with the project's own command (a Taskfile/
  3. Run the linter/formatter the project uses and fix what it flags.
  4. Re-read the request and confirm EVERY part is addressed — not just the
  5. Look for regressions — did the change break a caller, a contract, a test,

What it can do on your machine

Read from SKILL.md and the folder at commit 6d88d7f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Verification Before Completion loads about 432 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 241 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~432

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from duckbugio/flock at commit 6d88d7f, republished under its MIT licence (© duckbugio). 241 words, ~432 tokens.

Download SKILL.mdSave it as .claude/skills/verification-before-completion/SKILL.md (or your agent's skills folder).
name
verification-before-completion
description
Before telling the user a coding task is done, actually verify it — build, run the relevant tests/linter, and confirm the change does what was asked with no regressions. Use whenever you are about to claim a change is finished, fixed, or working.

Verify before you claim it's done

Saying "done" without checking is the most common way an agent ships a broken change. Before you report a coding task as finished, fixed, or working, VERIFY it — do not assume.

Checklist (do it, don't narrate it)

  1. Build / compile what you changed. If it doesn't build, it isn't done.
  2. Run the relevant tests with the project's own command (a Taskfile/ Makefile target, go test, npm test, …). Run the narrowest command that covers your change first, then the fuller suite if it's cheap. If the area you changed has no test and the change is non-trivial, add one.
  3. Run the linter/formatter the project uses and fix what it flags.
  4. Re-read the request and confirm EVERY part is addressed — not just the easy part. Check the edge cases and error paths you touched.
  5. Look for regressions — did the change break a caller, a contract, a test, or a neighbouring feature?

Reporting

  • Report what you actually ran and its result ("go test ./... green, task lint 0 issues"), never "should work".
  • If something failed, or you could not verify a part, SAY SO plainly — never paper over a failure or a skipped step.
  • If a test fails, fix the code (or the test, if the test was wrong) before claiming done — don't hand back a red build.

A task is "done" only when you have evidence it works, not when the code looks right.

© duckbugio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in core/skills/verification-before-completion of duckbugio/flock.

Open the folder on GitHubat commit 6d88d7f

Compare with similar skills

Verification Before Completion next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Verification Before Completion compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verification Before Completion this skillduckbugio/flock502—~432Automated safety check: PassMIT
Scope Creep Guardlennney/stop-that-shit2.5k1 repos~2kAutomated safety check: PassMIT
Validate Agent Workkryptamine/herdr-auto-title237—~605Automated safety check: PassMIT
Post-Feature Reviewjsmastery-pro/jsm-agent-skill218—~1.3kAutomated safety check: PassMIT
PUA Looptanweai/pua20k1 repos~1.1kAutomated safety check: PassMIT
Harness Engineering GuideOdradekAI/harness-engineering-guide1251 repos~4.3kAutomated safety check: PassApache-2.0

Similar skills

  • Scope Creep Guard

    lennney/stop-that-shit

    Keeps an agent focused on the requested work by applying a five-step ladder that checks for direct solutions, real gaps and speculative defenses before adding anything.

    2.5k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed
  • Validate Agent Work

    kryptamine/herdr-auto-title

    Final checklist before handing work back in the herdr-auto-title repo: review the diff, run make check, apply the comment and AGENTS.md rules, then report.

    237 GitHub stars~605 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Post-Feature Review

    jsmastery-pro/jsm-agent-skill

    Compares a finished feature with its plan, the project's architecture and design rules, and production-readiness checks, then reports issues without fixing them.

    218 GitHub stars~1.3k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • PUA Loop

    tanweai/pua

    Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.

    20k GitHub starsUsed in 1 repo~1.1k tokens
    Agent WorkflowsAuto-check passed
  • Harness Engineering Guide

    OdradekAI/harness-engineering-guide

    Audit, design, and implement AI agent harnesses for any codebase.

    125 GitHub starsUsed in 1 repo~4.3k tokens
    Agent WorkflowsAuto-check passed
  • Incremental Implementation

    addyosmani/agent-skills

    Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.

    103k GitHub starsUsed in 1 repo~2.3k tokens
    Agent WorkflowsAuto-check passed

More from duckbugio/flock

  • Looks up a third-party library's current documentation through the context7 MCP server instead of relying on the agent's possibly outdated training data.

    502 GitHub stars~408 tokensUpdated today
    Auto-check passed

Questions about Verification Before Completion

What does Verification Before Completion do?

Has the agent build, test and lint a change, re-read the request and check for regressions before it says a coding task is done, then report exactly what it ran. Before the agent reports a coding task as finished, fixed or working, this skill makes it gather evidence. The checklist covers building what changed, running the project's own test command (the narrowest command covering the change first, then the fuller suite if that is cheap), and running the project's linter or formatter.

When should I use Verification Before Completion?

Verification Before Completion fits situations like: about to tell the user a bug fix or feature is finished; wrapping up a change that touched several files or callers; before opening a pull request for a change the agent wrote.

How do I install Verification Before Completion in Claude Code?

Run `npx skills add duckbugio/flock --skill verification-before-completion -a claude-code`. Or copy the skill folder (core/skills/verification-before-completion in duckbugio/flock) into .claude/skills/verification-before-completion in your project. Claude Code loads it when a task matches its description.

How do I install Verification Before Completion in Codex?

Run `npx skills add duckbugio/flock --skill verification-before-completion -a codex`. Or copy the skill folder (core/skills/verification-before-completion in duckbugio/flock) into .agents/skills/verification-before-completion in your project. Codex loads it when a task matches its description.

Can I use Verification Before Completion in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add duckbugio/flock --skill verification-before-completion -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verification-before-completion, .gemini/skills/verification-before-completion, .github/skills/verification-before-completion and .opencode/skills/verification-before-completion in your project.

What does Verification Before Completion need to run?

Going by SKILL.md and its folder, Verification Before Completion needs the command-line tools its instructions call (go and npm). Our summary lists: A project with build, test or lint commands the agent can run.

Does Verification Before Completion access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Verification Before Completion safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Verification Before Completion use?

Verification Before Completion is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verification Before Completion use?

About 432 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Verification Before Completion?

Skills that share tags, products or a category with Verification Before Completion: Scope Creep Guard (lennney/stop-that-shit, 2.5k stars), Validate Agent Work (kryptamine/herdr-auto-title, 237 stars), Post-Feature Review (jsmastery-pro/jsm-agent-skill, 218 stars) and PUA Loop (tanweai/pua, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verification Before Completion?

duckbugio (a GitHub organization) maintains it in duckbugio/flock, which has 502 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 7, 2026.

Source: duckbugio/flock on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.