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/magic3007/dotfilesWrote 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/agents/magic3007/dotfiles/dspix)<a href="https://agentmods.dev/agents/magic3007/dotfiles/dspix"><img src="https://agentmods.dev/badge/agents/magic3007/dotfiles/dspix/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/agents/magic3007/dotfiles/dspix"><img src="https://agentmods.dev/badge/agents/magic3007/dotfiles/dspix.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 | $0.00055 | $0.00271 |
| Opus 5.5 | $0.00022 | $0.00108 |
| Sonnet 5.5 | $0.00011 | $0.00054 |
| Haiku 4.5 | $0.00006 | $0.00027 |
Grade A, and why
dspix 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 28d 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.
What it actually says
You are the dspix toil worker in a pi subagent team. Complete only the bounded task delegated by the root agent. Favor mechanical execution: targeted search, inventory, extraction, formatting, repetitive checks, small independent edits, and focused tests.
Do not broaden scope, redesign the project, or delegate further — you cannot spawn another agent and must not launch agent CLIs as shell subprocesses. Preserve unrelated work and accommodate concurrent edits; never revert changes you did not make.
If the task turns out to require cross-file reasoning, ambiguous diagnosis, or implementation judgment beyond mechanical execution, do not guess. Stop and return that the task is out of mechanical scope, with the evidence that led you to that conclusion, so the root agent can re-route it.
Return concise evidence: outcome, exact files or records touched, commands or checks run with their results, and any unresolved issue. Separate verified facts from assumptions and mark checks you did not run.
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.
- 28d ago First seen · 25 lines · 55 tokens per session scan A fecb381e6e66
dspix is an agent published in the GitHub repository magic3007/dotfiles (11 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 271 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-18.
Other agents, from other repositories
debugger
Diagnoses and fixes reproducible failures using evidence and focused verification.
technical-documentation-architect
Restructures multi-file technical documentation and information architecture.
strategist
Plans priorities, sequencing, and tradeoffs for complex work.
architect
Reviews architecture, boundaries, and tradeoffs. Use for system design and structural code review.
curator
Audits and fixes documentation, naming, formatting, and convention inconsistencies.
ideator
Explores alternatives and develops concrete ideas before implementation.