spec

A command for reviewing a feature specification, proposal, design, or task list before implementation. It checks areas such as scope, completeness, tasks, platform concerns, and how separate parts fit together.

In plain words
What is it for?
Use it before coding to review one or more specification files or folders, select review angles, and optionally iterate on fixes.
Why use it?
It helps expose missing details, risks, and unclear requirements while changes are still easier to make. An optional fix mode can run review-and-fix rounds.

Command

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 commands/shdennlin/agent-plugins/spec
Clone the repo
git clone --depth 1 https://github.com/shdennlin/agent-plugins
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,708 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 $0.00017 $0.01708
Opus 5 $0.00009 $0.00854
Sonnet 5 $0.00003 $0.00342
Haiku 4.5 $0.00002 $0.00171

Measured yesterday against content hash 48bed9000363, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec 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.

plugins/reviewer/commands/spec.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Review Command

Review feature specifications, proposals, designs, or task lists before implementation starts.

Multi-angle parallel review is the default — every invocation fans out across all built-in angles (scope, completeness, tasks, platform, and composition when the orchestrator judges multiple independent spec units are in scope). Use --angles to narrow that set; use --fix to also run an iterative review → fix loop.

Arguments

Parse the following from $ARGUMENTS:

  • [path...] — One or more file or folder paths to review (positional args)
  • --fix — After each review round, run an iterative fix loop. The orchestrator auto-fixes issues that don't need design judgment and escalates the rest to you (brainstorming-style) instead of using rigid severity rules
  • --angles <list> — Comma-separated list of angles to run (default: all built-in angles). Standalone flag; works with or without --fix
  • -n <N> or --max-iterations <N> — Maximum review-fix rounds, default 3 (only meaningful with --fix)
  • --no-explore — Skip codebase exploration step (go straight to review)
  • --help or -h — Show usage information and exit

Instructions

Step 1: Parse Arguments

From $ARGUMENTS, extract:

  1. help: if --help or -h is present, show the usage information below and stop. Do NOT delegate to the agent.
  2. paths: collect all positional arguments (not flags or flag values)
  3. fix_enabled: true if --fix is present
  4. no_explore: true if --no-explore is present
  5. angles: value after --angles (comma-separated string), or "default" if not provided
  6. max_iterations: integer value after -n or --max-iterations, default 3

Help Output

If --help or -h is present, display this and stop:

Usage: /reviewer:spec [path...] [options]

Review specs, proposals, or designs before implementation.

Every invocation runs multi-angle parallel review by default.

Positional arguments:
  path...                       One or more files or folders to review

Options:
  -h, --help                    Show this help message
  --no-explore                  Skip codebase exploration step
  --angles <list>               Comma-separated angles to run (default: all)
                                Available: scope, completeness, tasks, platform,
                                          design, consistency, composition
                                (composition auto-runs when the orchestrator judges
                                multiple independent spec units are in scope)

Fix mode options:
  --fix                         After each review, run an iterative fix loop.
                                The orchestrator auto-fixes issues that don't need
                                design judgment and escalates the rest to you.
  -n, --max-iterations <N>      Maximum review-fix rounds (default: 3)

Examples:
  /reviewer:spec docs/plans/auth-flow/              # all angles, review only
  /reviewer:spec proposal.md spec.md tasks.md
  /reviewer:spec                                    # asks which files to review

  # Iterative review + fix (default: 3 rounds)
  /reviewer:spec docs/plan/ --fix

  # Narrow to specific angles (review only)
  /reviewer:spec docs/plan/ --angles "scope,tasks"

  # Narrow angles + fix loop
  /reviewer:spec docs/plan/ --fix --angles "scope,tasks"

  # Skip codebase exploration
  /reviewer:spec docs/plan/ --no-explore

Read the full file on GitHub · 194 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. yesterday First seen · 194 lines · 17 tokens per session scan A 48bed9000363

Subscribe to this mod's changes

spec is a command published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 7d ago), licensed MIT. It adds 17 tokens to every session and 1,708 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 2026-08-31.