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 jnPiyush/AgentX --skill verification-before-completiongit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/verification-before-completion)<a href="https://agentmods.dev/skills/jnpiyush/agentx/verification-before-completion"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/verification-before-completion/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/jnpiyush/agentx/verification-before-completion"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/verification-before-completion.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 | $0.00054 | $0.01648 |
| Opus 5.5 | $0.00022 | $0.00659 |
| Sonnet 5.5 | $0.00011 | $0.00330 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
verification-before-completion scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Endpoint works | `curl -sfS http://localhost:PORT/health` | How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
WHEN: Any time the active agent is about to claim work is finished -- "done", "complete", "fixed", "tests pass", "loop complete", "ready for review", "deployed", "issue closed". The single most common Frontier failure mode is reporting completion that fresh verification would have caught.
When to Use This Skill
Load this skill when:
- An Engineer agent is about to close an issue or run
frontier loop complete - A Reviewer agent is about to set
APPROVED - A Tester agent is about to mark a test plan green
- A DevOps agent is about to claim a deployment succeeded
- Any agent is about to report results in chat without having re-run the check on the current commit
Skip when:
- The work is purely exploratory and no completion claim is being made
- The user has explicitly asked for a partial / in-progress report
Prerequisites
- Access to the verification surface (test runner, CLI, build, app under test, deployed URL)
- Knowledge of the exact command that proves the claim
- Current commit SHA or build identifier to anchor the evidence
Rationalization Table
Reject these six verification shortcuts.
| Rationalization | Reality |
|---|---|
| "The tests passed last time I ran them, the diff is small." | Old results are not a current pass. Label their revision and ask for post-loop test execution instead of inventing a rerun. |
| "The CI run on the previous commit was green." | Fresh commit, fresh run; a previous green run does not verify this commit. |
| "I can see by reading the code that it works." | Code inspection is necessary but insufficient to detect compiler, interpreter, or runtime failures. Run it. |
| "The change is too small to break anything." | Even a one-line change can break behavior. Run the verification. |
| "I need tests to say the loop is complete." | Loop/review verification uses acceptance mapping, independent findings and non-test checks. Do not run suites in those phases; ask the user after loop completion. Tests remain not run until approved and executed. |
| "The loop iteration count is satisfied, I can mark complete." | The count is a floor; the done criteria must pass on the current commit. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed · +4 lines 6d52a6a51c73
- 20d ago Changed · -16 tokens per session a9fbf62257e0
- 1mo ago Changed 4018870be7d2
- 1mo ago First seen · 142 lines · 70 tokens per session scan A d40ce4cf0935
verification-before-completion is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,648 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
cosmos-run-integration-tests
Run azure-cosmos integration/customer-workflow tests locally, closely following the CI pipeline (build+install, then failsafe verify with a test profile) using one consistent JDK for both steps. USE WHEN: asked to run cosmos integration tests, customer-workflow tests (fi-customer-workflows / fi-sm-customer-workflows)…
mantis-configure
Configures and validates Mantis pipeline environments, sandbox mechanisms, and AI models. Use to set up workflow.json, auto-detect host capabilities, switch between sandboxes (static-only, gvisor, microsandbox, gce), select AI models, and run fast 1-2s preflight tests. Don't use for scanning source code or running…
benchmark-workflow
Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.
user-story-writer
Escribir historias de usuario bien estructuradas con criterios de aceptación y casos extremos. Úsalo cuando te pidan escribir historias de usuario, crear tickets a partir de un resumen de características, convertir un PRD en historias o redactar criterios de aceptación. Produce historias listas para estimar en formato…