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/shdennlin/agent-plugins/specgit clone --depth 1 https://github.com/shdennlin/agent-pluginsWhat 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 | $0.00017 | $0.01708 |
| Opus 5 | $0.00009 | $0.00854 |
| Sonnet 5 | $0.00003 | $0.00342 |
| Haiku 4.5 | $0.00002 | $0.00171 |
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.
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)--helpor-h— Show usage information and exit
Instructions
Step 1: Parse Arguments
From $ARGUMENTS, extract:
- help: if
--helpor-his present, show the usage information below and stop. Do NOT delegate to the agent. - paths: collect all positional arguments (not flags or flag values)
- fix_enabled: true if
--fixis present - no_explore: true if
--no-exploreis present - angles: value after
--angles(comma-separated string), or "default" if not provided - max_iterations: integer value after
-nor--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
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 · 194 lines · 17 tokens per session scan A 48bed9000363
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.