Instructions for adding a new Forge tool, meaning an action the agent can call. They cover input and output validation, permissions, risk labels, sandboxed file and shell access, registration, and tests.

Implementing and registering tools, validating inputs, handling denied permissions as structured errors, testing path protection, and blocking dangerous shell commands.

They help ensure new tools report their side effects honestly, ask for permission before risky actions, and cannot escape the sandbox.

How hoangsonww/Forge-Agentic-Coding-CLI configures Claude Code and Cod

Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/Forge-Agentic-Coding-CLI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hoangsonww/Forge-Agentic-Coding-CLI/master/.agents/skills/add-tool/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-CLI

Made for: Claude Code, Codex.

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/skills/hoangsonww/forge-agentic-coding-cli/add-tool/github.svg)](https://agentmods.dev/skills/hoangsonww/forge-agentic-coding-cli/add-tool)

Your own site

<a href="https://agentmods.dev/skills/hoangsonww/forge-agentic-coding-cli/add-tool"><img src="https://agentmods.dev/badge/skills/hoangsonww/forge-agentic-coding-cli/add-tool/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/skills/hoangsonww/forge-agentic-coding-cli/add-tool"><img src="https://agentmods.dev/badge/skills/hoangsonww/forge-agentic-coding-cli/add-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 383 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	$0.00030	$0.00383
Opus 5.5	$0.00012	$0.00153
Sonnet 5.5	$0.00006	$0.00077
Haiku 4.5	$0.00003	$0.00038

Measured 2mo ago against content hash 05f70d00e24b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-tool 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 2mo 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.

.agents/skills/add-tool/SKILL.md · 47 lines

What it actually says

A new tool touches four places. Do all four or the tool is half-registered.

1. `src/tools/<name>.ts`

zod schemas for input and output.
Declare both sideEffect (none|read|write|network|exec) and risk (low|medium|high|critical) on the schema. Be honest — these drive the permission classifier.
All filesystem access goes through src/sandbox/fs.ts helpers.
All shell commands go through src/sandbox/shell.ts + classifyCommandRisk.
Request permission via requestPermission (src/permissions/manager.ts) before the side effect, not after.
Return { ok: true, data } / { ok: false, error }. Throw only for programmer errors, and then use ForgeRuntimeError.

2. Registration

Wire it into the registry, following the pattern of an existing tool like src/tools/read-file.ts.

3. `test/unit/<name>.test.ts`

Minimum coverage:

happy path with valid input,
zod rejection on invalid input,
permission denied → structured error (not throw),
sandbox refuses path-escape,
(if shell) critical command hard-blocked.

Use vi.mock for the permission manager and sandbox boundaries. No real filesystem writes outside os.tmpdir().

4. Docs

If user-visible, update the tools table in docs/ARCHITECTURE.md and the README "At a glance" count.

Finish with the verify skill.

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.

2mo ago First seen · 47 lines · 30 tokens per session scan A 05f70d00e24b

Subscribe to this mod's changes

add-tool is a skill published in the GitHub repository hoangsonww/Forge-Agentic-Coding-CLI (26 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 383 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 2026-08-30.

Building agents agentic-ai agentic-coding agentic-workflow agents cli command-line-interface

add-tool next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
add-toolhoangsonww/Forge-Agentic-Coding-CLI	Skill	26	1mo ago	MIT	A	30	Claude Code, Codex
code-revieweralirezarezvani/claude-code-tresor	Skill	782	4mo ago	MIT	A	54	Claude Code
git-commit-helperalirezarezvani/claude-code-tresor	Skill	782	4mo ago	MIT	A	55	Claude Code
test-generatoralirezarezvani/claude-code-tresor	Skill	782	4mo ago	MIT	A	55	Claude Code
readme-updateralirezarezvani/claude-code-tresor	Skill	782	4mo ago	MIT	A	49	Claude Code
api-documenteralirezarezvani/claude-code-tresor	Skill	782	4mo ago	MIT	A	48	Claude Code
dependency-auditoralirezarezvani/claude-code-tresor	Skill	782	4mo ago	MIT	A	51	Claude Code

Forge-Agentic-Coding-CLI: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

1. `src/tools/<name>.ts`

2. Registration

3. `test/unit/<name>.test.ts`

4. Docs

What this file has done since we first saw it

add-tool compared with skills from other repositories

Forge-Agentic-Coding-CLI: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

1. src/tools/<name>.ts

2. Registration

3. test/unit/<name>.test.ts

4. Docs

What this file has done since we first saw it

add-tool compared with skills from other repositories

1. `src/tools/<name>.ts`

3. `test/unit/<name>.test.ts`