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/disler/fixing-smartass-opus-5/installgit clone --depth 1 https://github.com/disler/fixing-smartass-opus-5Wrote 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/disler/fixing-smartass-opus-5/install)<a href="https://agentmods.dev/commands/disler/fixing-smartass-opus-5/install"><img src="https://agentmods.dev/badge/commands/disler/fixing-smartass-opus-5/install.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00649 |
| Opus 5 | $0.00015 | $0.00324 |
| Sonnet 5 | $0.00006 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
install 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 6d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Fixing Opus 5: System Prompt Engineering
Purpose
Set up this repo for the system prompt compare loop. Everything here is a CLI tool check: there are no dependencies to build and no env files to create. This is an interactive, agentic process — ask the user when choices are needed.
Variables
SOURCE_REPO: The directory this command is running from
SYSTEM_PROMPT: sr_opus_5_system_prompt.md
BENCHMARK_DOC: ai_docs/zuck-thefutureisforeveryone.md
Instructions
- Run every check via Bash — do not assume anything is installed.
- Show a status line immediately after each check (pass or fail).
- For auto-installable items (herdr, jq, pi), install them without asking.
- Never start claude, pi, or herdr sessions — only verify the binaries respond.
- Model access (Anthropic auth) is the user's own login; do not read or display any credentials.
Workflow
Step 1 — Check Prerequisites
Critical (gate — stop and guide the user if missing):
command -v just— task runner. Install:brew install just(or https://github.com/casey/just).command -v claude— Claude Code CLI. Install: https://docs.claude.com/cli. Required forjust sr-opus,just smart-ass-opus,just compare.
Standard (auto-install if missing):
command -v herdr— terminal agent multiplexer, required byjust compareandjust pi-compare. Install:brew install herdr(https://herdr.dev).command -v jq— JSON parsing inside the compare recipes. Install:brew install jq.command -v pi— Pi coding agent, required only for thejust sr-pi,just smart-ass-pi, andjust pi-comparemirror recipes. Install:npm install -g @mariozechner/pi. If npm is unavailable, mark as skipped and note the pi recipes will not work.
Step 2 — Verify Repo Files
- Confirm
SYSTEM_PROMPTexists and is non-empty — it is the entire product. - Confirm
BENCHMARK_DOCexists — the compare recipes prompt against it. - Run
just --list— confirms the justfile parses and shows all seven recipes.
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.
- 6d ago First seen · 57 lines · 29 tokens per session scan A 32717dc58f38
install is a command published in the GitHub repository disler/fixing-smartass-opus-5 (314 stars, last pushed 20d ago), licensed MIT. It adds 29 tokens to every session and 649 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 2026-08-30.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.