command-surface

A checklist for adding, renaming, or removing a Forge command file. It covers the generated command list, command registry, skill ownership, and tests needed for the command to work everywhere.

In plain words
What is it for?
Use it when changing files in lib/commands/ or when a manifest-drift or unresolved-command error appears. It helps register the command, regenerate its manifest, assign skill coverage, and add its test lane.
Why use it?
Changing one command file can leave generated metadata, command lookup, or test coverage out of date. The checklist catches those connected changes before the build or tests fail.

Skill for Claude CodeCodex

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/harshanandak/forge/command-surface
Any agent
npx skills add harshanandak/forge --skill command-surface
Clone the repo
git clone --depth 1 https://github.com/harshanandak/forge

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 661 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.00661
Opus 5 $0.00027 $0.00331
Sonnet 5 $0.00011 $0.00132
Haiku 4.5 $0.00005 $0.00066

Measured 2d ago against content hash bdaeae868a98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-surface 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 2d 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.

.forge/contributor-skills/command-surface/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

command-surface

A command file is five surfaces, not one. Add the file and stop, and the compiled binary breaks while dev-mode auto-discovery hides it from you.

The surfaces

Adding, renaming, or removing lib/commands/<name>.js means all of these:

  1. Manifest — regenerate the static require graph:

    node scripts/gen-command-manifest.js          # write if changed
    node scripts/gen-command-manifest.js --check  # exit 1 if stale
    

    lib/commands/_manifest.js is generated; never hand-edit it. Drift is enforced by test/structural/command-manifest-drift.test.js. [verified 2026-08-13]

  2. Registry — the command must resolve through the CLI registry (test/forge-cli-registry.test.js, test/cli-flags.test.js).

  3. Skill coverageskills/coverage.json maps every registered user-facing command to an owning skill, or carries an explicit { exempt: <reason> }. Enforced by evaluateCoverage in lib/skill-eval.js and gated in test/skill-eval.test.js. [verified 2026-08-13]

  4. Test lane — an entry in DIRECT_TEST_CANDIDATES (lib/commands/test.js) so the new file resolves to real tests instead of forcing the full suite. See the test-lane skill.

  5. Documentation — the command help text and, if it is a stage or utility, its row in AGENTS.md.

Rules

  • Regenerate, never hand-write, the manifest. Dev-mode discovery masks a stale manifest locally; bun build --compile and the drift gate do not.
  • Exempt means complete, not deferred. A command leaves coverage.json as exempt only when it is genuinely mapped, routable, and documented — and only in the PR that owns it. A hollow mapping just draws review rounds.
  • Use Forge's own generator. Re-implementing what the skill CLI already does is a recurring correction here: "why should we do the work". One canonical source, everything else generated. [Forge #5 ×4]
  • Names stay short. status, ready, ship, trace. Long or technical command names are a taste failure in this CLI.

Read the full file on GitHub · 63 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.

  1. 2d ago First seen · 63 lines · 54 tokens per session scan A bdaeae868a98

Subscribe to this mod's changes

command-surface is a skill published in the GitHub repository harshanandak/forge (4 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 661 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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