An end-to-end engineering workflow that plans, builds, reviews, tests, and finalizes a feature or fix. It can run some steps in parallel when given `--swarm`.

Use it to create a plan, implement it, review the changes, test browser behaviour, resolve findings, and add a feature walkthrough.

It removes the need to remember and coordinate the usual development steps from an idea through pull-request checks.

ia-lfg — Command for Claude Code by iliaal

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.

Clone the repo

git clone --depth 1 https://github.com/iliaal/whetstone

Made for: Claude Code.

Or install whetstone, the plugin that ships this one along with the rest of its 32 skills, 22 commands, 19 agents, 1 hook, 1 MCP server.

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/iliaal/whetstone/ia-lfg/github.svg)](https://agentmods.dev/commands/iliaal/whetstone/ia-lfg)

Your own site

<a href="https://agentmods.dev/commands/iliaal/whetstone/ia-lfg"><img src="https://agentmods.dev/badge/commands/iliaal/whetstone/ia-lfg/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/iliaal/whetstone/ia-lfg"><img src="https://agentmods.dev/badge/commands/iliaal/whetstone/ia-lfg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 734 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	$0.00017	$0.00734
Opus 5	$0.00009	$0.00367
Sonnet 5	$0.00003	$0.00147
Haiku 4.5	$0.00002	$0.00073

Measured yesterday against content hash 3a1955e08a38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ia-lfg 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.

plugins/whetstone/commands/ia-lfg.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run these steps in order. Do not stop between steps -- complete every step through to the end.

Mode detection: If $ARGUMENTS contains --swarm, use swarm mode (parallel execution in steps 4-6). Otherwise run sequentially.

Arguments guard: If $ARGUMENTS is empty (no feature description and no --swarm), ask for a feature description before proceeding. Do not invoke /ia-plan with empty input.

Sequential steps

/ia-plan $ARGUMENTS (strip --swarm from arguments if present)
/ia-deepen-plan (auto-detects latest plan in docs/plans/)

Build

/ia-work

Swarm mode: Use Task list and launch parallel agent swarm subagents to build the plan. Normal mode: Execute sequentially.

Verify (parallel in swarm mode)

/ia-review
/ia-test-browser

Swarm mode: Launch steps 4 and 5 as parallel background Task agents. Wait for both to complete. Normal mode: Run sequentially.

Finalize

/ia-resolve-todo-parallel -- resolve any findings from review
/ia-feature-video -- record walkthrough and add to PR

CI watch (after PR opens)

Before polling: distinguish actionable CI failures from non-actionable gates. Run gh pr view --json isDraft,reviewDecision plus gh pr checks --json name,state,bucket (the bucket field categorizes state into pass, fail, pending, skipping, or cancel; there is no conclusion field on this subcommand). Add --required to see only required checks. Classify by bucket, not vendor name:
- bucket: fail on a required check (gh pr checks --required --json name,state,bucket) -> actionable, fix in Step 9.
- isDraft: true with no checks after a grace period -> stop and report DRAFT_PR_WITH_NO_CHECKS. Do not mark ready for review unless asked.
- reviewDecision: REVIEW_REQUIRED or any human-approval gate with no failing checks -> stop and report BLOCKED_BY_REVIEW_GATE. Human review is not an actionable failure.
- No checks registered after a grace period -> stop and report NO_CHECKS_REGISTERED.
- bucket: skipping/cancel, or bucket: pending on non-required checks -> do not wait. Required-status-checks (configurable via gh api repos/{owner}/{repo}/branches/{branch}/protection) are the source of truth; common examples include test/lint/build jobs and code-review bots (Sentry, Codecov, Cursor, BugBot, etc.) — treat each by its bucket, not its name.
Poll CI for the new PR. On failure: read the job log, identify the root cause, fix, push. Cap at 3 fix iterations.
Do NOT weaken, skip, or mock the failing assertion to make CI green -- repair the actual issue. If genuinely flaky after 3 iterations, document the residual in the PR body and stop.

Read the full file on GitHub · 51 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 · 51 lines · 17 tokens per session scan A 3a1955e08a38

Subscribe to this mod's changes

ia-lfg is a command published in the GitHub repository iliaal/whetstone (33 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 734 once invoked, about $0.0001 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 2026-09-07.

Planning Project management agent-skills ai-agents ai-tools claude-code-plugin

ia-lfg

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Sequential steps

Build

Verify (parallel in swarm mode)

Finalize

CI watch (after PR opens)

What this file has done since we first saw it

Other commands, from other repositories

risk-log

raci

apollo-tasks

update-jira

f5-implement

f5-import