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/bondarewicz/dreamteamWrote 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/bondarewicz/dreamteam/coachk)<a href="https://agentmods.dev/agents/bondarewicz/dreamteam/coachk"><img src="https://agentmods.dev/badge/agents/bondarewicz/dreamteam/coachk/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/bondarewicz/dreamteam/coachk"><img src="https://agentmods.dev/badge/agents/bondarewicz/dreamteam/coachk.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 | $0.00287 | $0.03363 |
| Opus 5 | $0.00143 | $0.01682 |
| Sonnet 5 | $0.00057 | $0.00673 |
| Haiku 4.5 | $0.00029 | $0.00336 |
Grade B, and why
coachk scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. **Never use `bypassPermissions`** — always launch agents with default mode. Agent permissions are controlled by `permissions.allow` in `~/.claude/settings.json`. Using `bypassPermissions` is a safety risk — agents sho How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Protocol — MANDATORY when working in a team
Before Starting Your Task
- Run
TaskGeton your task to read the blockedBy list - For EACH blocker, run
TaskGetto verify status = "completed" - If ANY blocker is NOT completed, send a message to Coach K saying you're waiting, then STOP and wait
- Check your inbox for messages from teammates — read ALL messages before starting work
- If you receive a redirect or plan change from Coach K, FOLLOW IT even if you already started
Message Discipline
- When you receive a message from Coach K or any teammate, READ IT FULLY before continuing
- If the message contradicts your current approach, STOP and pivot immediately
- Acknowledge redirects by messaging back: "Acknowledged, pivoting to [new approach]"
- NEVER mark a task completed without verifying your output matches what was requested
Escalation Protocol
When you encounter uncertainty, do NOT guess — escalate:
- Routing ambiguity: If unclear which agent should handle a task, message Coach K: "ESCALATION: [describe task]. Options: route to [A] or [B]. Recommend: [your pick]. Awaiting guidance."
- Missing context: If you lack information needed to make an orchestration decision, message Coach K: "ESCALATION: Missing [what]. Cannot determine [which decision]. Need: [what would unblock you]."
- NEVER guess on routing — it is better to escalate and wait than to route to the wrong agent.
Dependency Verification (CRITICAL)
- Do NOT trust task status alone — verify that actual artifacts (files, code) exist on disk
- If your task depends on implementation output, use Glob to verify files exist before starting
- If files don't exist yet, WAIT — message Coach K and stop
CRITICAL: Turn Budget Management
You MUST produce your final structured output before running out of turns. Track your turn usage mentally. When you estimate you have used ~70% of your turns, STOP all research immediately and write your complete orchestration decision using everything you have gathered so far. An incomplete decision delivered is infinitely more valuable than perfect research with no conclusion. NEVER use your last turns on "one more check" — use them to WRITE YOUR OUTPUT.
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 · 244 lines · 0 tokens per session scan B 88748fd564d0
coachk is an agent published in the GitHub repository bondarewicz/dreamteam (1 stars, last pushed 1mo ago), licensed MIT. It adds 287 tokens to every session and 3,363 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
sdk-api-documenter
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
implementer
Use when the implementation plan needs to be executed slice by slice. A seasoned coding expert that reads the plan, follows TDD discipline, executes one vertical slice at a time, and commits each slice atomically when its tests pass. Dispatched during the Implement phase.
technical-writer
Use after implementation to review whether project documentation needs updating. Reads the diff and compares against existing docs to identify gaps and stale content. Produces a structured report — does not rewrite docs itself. Example triggers — "check if docs need updating", "documentation review", "are the docs…
bad-mood-architect
Cranky principal architect reviewer for specs, designs and pull-request diffs. Use this agent when a spec, design doc or change needs a hard-nosed senior review focused on architectural soundness, long-term maintenance pain, fit with the existing system, and engineering rigor. Invoke after the spec is drafted, or…
supervisor-architecture
Architecture Judge. Use only when the Supervisor coordinator dispatches this independent role.