A command that starts, inspects, relaxes, or ends an enforced coding task. During a task, it can protect existing test files and require the project's test command to pass before stopping.

Use it when implementing a change that needs test-file protection and a required test run before completion.

It prevents changes to selected existing tests and stops work from being declared complete while the recorded tests are failing.

task — Command for Claude Code by nxtg-ai/forge-plugin

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add nxtg-ai/forge-plugin

Claude Code

/plugin install nxtg-forge

Made for: Claude Code.

Or install nxtg-forge, the plugin that ships this one along with the rest of its 27 skills, 24 commands, 33 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/task/github.svg)](https://agentmods.dev/commands/nxtg-ai/forge-plugin/task)

Your own site

<a href="https://agentmods.dev/commands/nxtg-ai/forge-plugin/task"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/task/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/nxtg-ai/forge-plugin/task"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 729 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00027	$0.00729
Opus 5.5	$0.00011	$0.00292
Sonnet 5.5	$0.00005	$0.00146
Haiku 4.5	$0.00003	$0.00073

Measured 6d ago against content hash b39c01d30158, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task 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 6d 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.

plugins/nxtg-forge/commands/task.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NXTG-Forge Enforced Task

The user ran this command, and the step below has already run. Its output is the result:

!node "${CLAUDE_PLUGIN_ROOT}/scripts/forge-task.mjs" cli $ARGUMENTS

Report that output to the user in one or two lines. Do not run forge-task.mjs yourself: while a task is active only the user begins, relaxes or ends it. The guard refuses a Bash command that names the engine's begin, mode or abort subcommands, or the task-state directory, in plain text. It is a text check, so it does not stop a glob, a variable or a script that reaches the state.

What an enforced task does

While a task is active in this project:

Write guard (PreToolUse). Edits to a test file that existed when the task began, and to test-runner config (conftest.py, pytest.ini, jest.config.*, and similar), are refused, with the file and the reason. New test files are allowed. In tests mode nothing is refused.
Stop gate (Stop). Stopping is blocked until the test command recorded at begin passes, with the baseline tests and the test command unchanged. Alternatively, it ends when .claude/forge-conflict-report.json shows that a test contradicts the spec, and every cited line checks out against the files. After the configured number of blocked stops (default 5), the task ends as unearned, which means not done.
What it does not check: that the tests cover the new behaviour. It checks only that the project's own tests pass without being weakened.

Subcommands

Subcommand	Effect
`begin [--mode implement\|tests] [--test-cmd "<cmd>"] [--max-blocks N] [--timeout S]`	Records the test files, the test command and the base commit. It refuses to begin when no test command can be found.
`status`	Shows the task's mode, test command, blocked-stop count and verdict.
`tests`	Lets the agent change tests. Use it when the task is to write or fix tests.
`implement`	Back to implementation. The tests as they are now become the new baseline.
`abort`	Ends the task without a check. The verdict is `aborted`.

Read the full file on GitHub · 43 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.

6d ago First seen · 43 lines · 27 tokens per session scan A b39c01d30158

Subscribe to this mod's changes

task is a command published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 729 once invoked, about $0.0001 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 2026-10-14.

Claude Code Testing ai ai-agents ai-development claude coding-assistant

maintainer-review-test-coverage

Review the PR for test coverage — does new behavior have tests, are critical paths exercised, do existing tests still cover what they should (Pi-tuned).

coleam00/Archon · 31 tokens

discover-checks

Find the project's own checks and declare them. You do not run the gate: a script runs exactly what you declare, for as long as it takes, and records every exit status. Your declaration is the whole of what gets validated, so it must be the project's gate and nothing else.

coleam00/Archon · 0 tokens

e2e-echo-command

E2E test command — echoes back the user message.

coleam00/Archon · 11 tokens

expect

Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…

yonatangross/orchestkit · 73 tokens

kill-mutants

Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.

swingerman/engineer · 29 tokens

paul:verify

Guide manual user acceptance testing of recently built features.

ChristopherKahler/paul · 14 tokens