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 skills add Jamie-BitFlight/claude_skills --skill multi-perspective-reviewgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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.
[](https://agentmods.dev/skills/jamie-bitflight/claude_skills/multi-perspective-review)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/multi-perspective-review"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/multi-perspective-review/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.
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/multi-perspective-review"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/multi-perspective-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 324 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00073 | $0.03737 |
| Opus 5 | $0.00036 | $0.01869 |
| Sonnet 5 | $0.00015 | $0.00747 |
| Haiku 4.5 | $0.00007 | $0.00374 |
Grade A, and why
multi-perspective-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Perspective Review
Role
Dispatches every worker — the four reviewers and the synthesizer — as dh:task-worker, never a
specialist agent directly, so each can claim and close its own SAM task (see Behavioral Rules). The
gate in Step 7 applies to the synthesizer's punch list, not to the four raw verdicts.
Activate dh:review-verdict-contract before the first verdict-schema operation.
Argument Parsing
| Argument | Type | Description |
|---|---|---|
--diff <git-range> |
required | Passed to git diff --name-only. Commit outstanding changes first, then pass <base>..HEAD, where <base> is a commit SHA captured before this work's first commit — the caller is responsible for supplying one that still resolves. |
--issue <N> |
optional | GitHub issue number used for ephemeral plan linkage and slug derivation. |
--slug <str> |
optional | Explicit slug override. When omitted, derived from --issue or current git branch. |
Parse arguments from the invocation arguments string. Abort with usage message if --diff is
absent.
Step 1: Resolve Changed Files
Run:
git diff --name-only <git-range>
Split stdout by newline. Trim empty lines. This is the changed_files list.
Abort condition: If changed_files is empty, print the following and stop:
ERROR: No changed files found for diff range <git-range>. Nothing to review.
Do not create a plan when changed_files is empty.
Step 2: Derive Review Slug
Derive review_base exactly once using this flowchart:
flowchart TD
Start([Derive review_base]) --> Q1{--slug argument provided?}
Q1 -->|Yes| A["review_base = --slug value"]
Q1 -->|No| Q2{--issue N argument provided?}
Q2 -->|Yes| B["review_base = review-{N}<br>e.g. review-2181"]
Q2 -->|No| C["git rev-parse --abbrev-ref HEAD<br>review_base = review-{branch-name}<br>sanitize: replace / with -"]
Run this command and capture its stdout as run_stamp:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed 12ca24d548a4
- 7d ago First seen · 357 lines · 73 tokens per session scan A a8f82f2e4b6b
multi-perspective-review is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 3,737 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…