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.
git clone --depth 1 https://github.com/MotleyAI/slayerWrote 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/commands/motleyai/slayer/spec)<a href="https://agentmods.dev/commands/motleyai/slayer/spec"><img src="https://agentmods.dev/badge/commands/motleyai/slayer/spec/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/commands/motleyai/slayer/spec"><img src="https://agentmods.dev/badge/commands/motleyai/slayer/spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00989 |
| Opus 5.5 | $0.00000 | $0.00396 |
| Sonnet 5.5 | $0.00000 | $0.00198 |
| Haiku 4.5 | $0.00000 | $0.00099 |
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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Defines the slayer command line's user-facing contract: how errors are reported, the version and
debug flags, the search and sample-refresh command shapes, and how query results print as a table.
ADDED Requirements
Requirement: CLI errors are one line on stderr
When any slayer command fails with an exception, the CLI SHALL print exactly one line to stderr
and exit with status 1, printing no traceback. A SLayer error SHALL print as Error: <message>; any
other exception SHALL print as Error: <exception class>: <message> (rerun with --debug for the traceback). Every error message a command prints SHALL go to stderr, never stdout. An interrupt or an
explicit exit SHALL keep its own behaviour.
Scenario: A failing query prints one line
- WHEN
slayer queryruns a query whose dimension no join path reaches - THEN stderr holds one line starting
Error:with the SLayer error's message, stdout is empty of error text, and the exit status is 1
Scenario: An unexpected error names its class and the debug flag
- WHEN a command fails with a database driver error
- THEN stderr holds one line naming the exception class, its message and
--debug, and the exit status is 1
Requirement: --debug shows the traceback
Every slayer command SHALL accept --debug, written before or after the command and its
subcommand; with it, a failing command SHALL print the full traceback.
Scenario: --debug in any position
- WHEN a failing command runs as
slayer --debug query …, asslayer query … --debug, or asslayer datasources refresh-samples --debug - THEN each prints the full traceback
Requirement: slayer --version
slayer --version SHALL print slayer <installed package version> and exit with status 0.
Scenario: Version is printed
- WHEN
slayer --versionruns - THEN stdout is
slayer <version>, where<version>is the installedmotley-slayerversion
Requirement: search takes its question positionally
slayer search SHALL accept the free-text question as an optional positional argument and SHALL keep
accepting it as --question; giving both SHALL fail as a CLI error. A positional question equal to
refresh-samples SHALL fail with an error telling the user to run slayer datasources refresh-samples.
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.
- 8d ago First seen · 79 lines · 0 tokens per session scan A 172d150b6cd0
spec is a command published in the GitHub repository MotleyAI/slayer (334 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 989 tokens. 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 2026-10-29.
spec compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| specMotleyAI/slayer | Command | 334 | yesterday | MIT | A | 0 | Claude Code |
| prototypegrainulation/grainulator | Command | 86 | yesterday | MIT | A | 0 | Claude Code |
| qa-changesOpenHands/extensions | Command | 176 | yesterday | MIT | A | 63 | Claude Code |
| verifycloudnative-co/claude-code-starter-kit | Command | 153 | 25d ago | MIT | A | 9 | Claude Code |
| modernize-transformfuxicodex/Fuxi | Command | 3.2k | 17d ago | none | A | 17 | Claude Code |
| constraintsvinvcn/addyosmani-agent-skills-zh | Command | 46 | 17d ago | MIT | A | 20 | Claude Code |
| check-devpunt-labs/z-spec | Command | 5 | yesterday | MIT | A | 7 | Claude Code |