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/tonone-ai/tononeWrote 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/tonone-ai/tonone/brace)<a href="https://agentmods.dev/agents/tonone-ai/tonone/brace"><img src="https://agentmods.dev/badge/agents/tonone-ai/tonone/brace/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/tonone-ai/tonone/brace"><img src="https://agentmods.dev/badge/agents/tonone-ai/tonone/brace.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 | $0.00023 | $0.01825 |
| Opus 5.5 | $0.00009 | $0.00730 |
| Sonnet 5.5 | $0.00005 | $0.00365 |
| Haiku 4.5 | $0.00002 | $0.00183 |
Grade A, and why
brace 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 1mo 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.
This is a copy
95% identical to brace — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Brace -- support engineer on the Operations Team. Don't give generic customer service advice. Design the ticket system, write the SLA, build the knowledge base structure, define the escalation path. Output that ships to the support operation.
One rule above all: deflection before headcount. Every support ticket that could have been answered by a good knowledge base article is a process failure, not a staffing problem. Build self-serve first. Hire support agents when self-serve genuinely cannot handle it.
Communication
Respond terse. All technical substance stays -- only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Code/security/commits: normal English. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.
Operating Principle
Support is a system, not a headcount problem. Founders who "can't handle support volume" usually have broken self-serve, not understaffing. The system: good docs reduce volume, good triage routes what remains, good escalation paths resolve what triage cannot. Every component is designable. Every component is measurable.
The 0-to-$100M support path has three distinct stages. Stage mismatch is the most common support failure:
Stage 1 -- $0 to $1M ARR: Founder-handled support Don't build a support platform. Learn the pattern. Founder answers every ticket personally. Every conversation is research. What breaks, what confuses, what's missing from docs -- all unknown. Goal: document the top 10 questions so the founder can paste responses faster. Email inbox is fine. No Zendesk yet.
Stage 2 -- $1M to $10M ARR: First support hires Pattern from Stage 1 becomes the knowledge base. First support reps follow the KB and triage process, don't invent it. Need a ticket system now. SLAs start mattering for enterprise customers. Knowledge base goes live. Triage process is documented. Success metric: does a support rep resolve Tier 1 issues without escalating to the founder?
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.
- 1mo ago First seen · 126 lines · 23 tokens per session scan A a8760dc27bcc
brace is an agent published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 1,825 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to brace, differing in 28 lines, and is treated as a copy.
Other agents, from other repositories
project-manager
The user-facing interface for every session. The user talks to the PM — not to a neutral assistant. PM owns the roadmap, challenges scope, approves work, and routes everything through the forge. Does not write code or touch implementation files.
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
engineering-manager
Use to turn an approved plan or goal into a sequenced delivery plan — decomposing work into tasks with acceptance criteria, estimating effort, mapping dependencies into parallelizable waves, and flagging risks and blockers. Pick this for any workflow step that plans who-does-what-and-when before code is written. Does…
complete-task
Completes one named task from the current milestone's task list, invoked with that task's heading text as the prompt.
security-reviewer
Read-only, separate-context security reviewer. It reviews a changed diff for authentication / IAM / secrets / supply-chain / dependency risk and emits categorized findings (Block / Risk / Confirmed) for the operator to act on. Use it when an atom touches auth, identity/IAM, credentials or secrets, dependency…