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/code-reviewgit 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 | $0.00010 | $0.01930 |
| Opus 5 | $0.00005 | $0.00965 |
| Sonnet 5 | $0.00002 | $0.00386 |
| Haiku 4.5 | $0.00001 | $0.00193 |
Grade A, and why
code-review 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General Guidelines
Code Review
Perform a code review using dynamic category detection.
Phase 0: Setup & Categorization
Determine What to Review
Parse the argument to determine the review target:
| Input | Action |
|---|---|
| No argument | Detect divergence point, confirm scope with user |
| Branch name | Use specified branch as base |
PR number (e.g., 123) |
Fetch PR diff from GitHub |
PR URL (e.g., https://github.com/owner/repo/pull/123) |
Extract PR number and fetch diff |
For GitHub PRs:
- Use
ghCLI to fetch the diff:gh pr diff <number> - If the command fails, report error and stop
For local branches (no argument or branch name provided):
-
Get current branch:
git rev-parse --abbrev-ref HEAD -
Check for uncommitted changes:
git status --porcelain- If output is non-empty, note that uncommitted changes exist
-
Detect divergence point (skip if branch name was provided as argument):
- Get all local branches except current:
git branch --format='%(refname:short)' - For each branch, find merge-base:
git merge-base HEAD <branch> - Count commits from merge-base to HEAD:
git rev-list --count <merge-base>..HEAD - The branch with the fewest commits back (closest merge-base) is the likely parent
- If no other branches exist, fall back to
main,master, ordevelopif they exist as remote tracking branches
- Get all local branches except current:
-
Confirm scope with user using
AskUserQuestion:Question 1 - "Review scope" (header: "Base branch"):
- Option A:
From <detected-branch>— "Review N commits since diverging from " - Option B:
Different branch— "Specify another branch to compare against" - Option C:
Uncommitted only— "Review only staged/unstaged changes, skip committed work"
- Option A:
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.
- today First seen · 253 lines · 10 tokens per session scan A fe5a45e1577c
code-review is a command published in the GitHub repository christopher-buss/bedrock (13 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 1,930 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 2026-09-01.
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.review
Review the active spec, plan, tasks, staged changes, or branch for security and governance gaps.
sicario.threatmodel
Create or update docs/security/threat-model.md from the active spec and plan.