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 agentmods add commands/christopher-buss/bedrock/add-commandgit clone --depth 1 https://github.com/christopher-buss/bedrockWhat 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 | $0.00006 | $0.01061 |
| Opus 5 | $0.00003 | $0.00531 |
| Sonnet 5 | $0.00001 | $0.00212 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
add-command 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.
This is a copy
86% identical to add-command — 76 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slash Command Creator Guide
How This Command Works
The /add-command command shows this guide for creating new slash commands. It
includes:
- Command structure and syntax
- Common patterns and examples
- Security restrictions and limitations
- Frontmatter options
Note for AI: When creating commands, you CAN use bash tools like
Bash(mkdir:*), Bash(ls:*), Bash(git status:*) in the allowed-tools
frontmatter of NEW commands - but ONLY for operations within the current project
directory. This command itself doesn't need bash tools since it's just
documentation.
Command Locations
- Personal:
~/.claude/commands/(available across all projects) - Project:
.claude/commands/(shared with team, shows "(project)")
Basic Structure
---
allowed-tools: Read, Glob, Grep, Bash(git status:*), Task
description: Brief description of what this command does
argument-hint: [required-arg] [optional-arg]
---
# Command Title
Your command instructions here.
Arguments: $ARGUMENTS
File reference: @path/to/file.js
Bash command output: (exclamation)git status(backticks)
⚠️ Security Restrictions
Bash Commands (exclamation prefix): Limited to current working directory only.
- ✅ Works:
! + backtick + git status + backtick(in project dir) - ❌ Blocked:
! + backtick + ls /outside/project + backtick(outside project) - ❌ Blocked:
! + backtick + pwd + backtick(if referencing dirs outside project)
File References (@ prefix): No directory restrictions.
- ✅ Works:
@/path/to/system/file.md - ✅ Works:
@../other-project/file.js
Common Patterns
Simple Command
echo "Review this code for bugs and suggest fixes" > ~/.claude/commands/review.md
Command with Arguments
Note for AI: The example below uses a fullwidth dollar sign (＄, U+FF04) to
prevent interpolation in this documentation. When creating actual commands, use
the regular $ character.
Fix issue ＄ARGUMENTS following our coding standards
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 · 167 lines · 6 tokens per session scan A 505432aa2026
add-command is a command published in the GitHub repository christopher-buss/bedrock (13 stars, last pushed yesterday), licensed MIT. It adds 6 tokens to every session and 1,061 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to add-command, differing in 76 lines, and is treated as a copy.
Other commands, from other repositories
sicario.verify
Run deterministic verification.
create-plan
Important: ALL phases must use checkmarks for their tasks. Each checkmark should correspond to a single commit. The checkmark should be marked - [x] in the same commit that completes the task. Phase tasks should be prefixed with parent phase number and letters (a, b, c, etc.).
sicario.controls
Generate or update docs/compliance/control-applicability.md.
sicario.assess
Assess the repository against SicarioSpec guardrails.
sicario.init
Initialize SicarioSpec files in the current repository.
sicario.review
Review the active spec, plan, tasks, staged changes, or branch for security and governance gaps.