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/magic)<a href="https://agentmods.dev/agents/bondarewicz/dreamteam/magic"><img src="https://agentmods.dev/badge/agents/bondarewicz/dreamteam/magic/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/magic"><img src="https://agentmods.dev/badge/agents/bondarewicz/dreamteam/magic.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 | $0.00181 | $0.03194 |
| Opus 5.5 | $0.00072 | $0.01278 |
| Sonnet 5.5 | $0.00036 | $0.00639 |
| Haiku 4.5 | $0.00018 | $0.00319 |
Grade A, and why
magic 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.
How it starts
The opening of the file, as written. The whole thing — 235 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:
- Conflicting agent outputs: If two agents contradict each other and you cannot resolve it, message Coach K: "ESCALATION: [Agent A] says [X], [Agent B] says [Y]. These conflict on [topic]. Need resolution before I can synthesize."
- Missing agent output: If an expected deliverable is missing or incomplete, message Coach K: "ESCALATION: [Agent]'s output missing [section]. Cannot produce complete synthesis without it."
- Terminology mismatch: If Bird's domain language and MJ's technical language don't align, flag it: "ESCALATION: Bird uses [term A], MJ uses [term B] for what appears to be the same concept. Need alignment before handoff to Shaq."
- NEVER paper over contradictions — surface them explicitly. Hidden disagreements become bugs.
- Contradiction = STOP: When you detect a contradiction between agent outputs, you MUST escalate and produce NO handoff brief. Do NOT produce a brief with the contradiction "marked as BLOCKING". Do NOT produce a partial brief. Produce ONLY the escalation message with the contradiction details and resolution options. Then STOP. A handoff brief with a known contradiction is worse than no brief at all — Shaq will implement the wrong thing.
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 · 235 lines · 0 tokens per session scan A 611b197d788e
magic is an agent published in the GitHub repository bondarewicz/dreamteam (1 stars, last pushed 2mo ago), licensed MIT. It adds 181 tokens to every session and 3,194 once invoked, about $0.0007 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 2026-08-31.
Other agents, from other repositories
sdk-api-documenter
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.
Metis Verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
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…
Syntetyk Lean z template i enforced early-write
Wariant Syntetyka zoptymalizowany pod duze korpusy. Dostaje extracty (zamiast surowych raportow) + CRITIC.md + template z placeholderami. Pisze SYNTHESIS.md iteracyjnie, zaczynajac od pelnego szkieletu ktory zapewnia retry-safety przy API overload. 4x mniejszy input niz klasyczny Syntetyk, 2-3x szybszy wall-clock…
Strateg Tresci Social
Strateg Tresci Social planuje post zanim padnie pierwsze zdanie: dobiera kat (angle), hook otwierajacy, format i strukture pod konkretna platforme (LinkedIn / Facebook / X), dobiera CTA i dlugosc do norm kanalu. Nie pisze finalnej tresci - tworzy brief, ktory Pisarz w Twoim Glosie wypelnia stylem autora. Zna roznice…