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/PrendsTaPart/Plugin-Claude-MCP-BraindCode-Wrote 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/prendstapart/plugin-claude-mcp-braindcode-/exploitation)<a href="https://agentmods.dev/agents/prendstapart/plugin-claude-mcp-braindcode-/exploitation"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/exploitation/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/prendstapart/plugin-claude-mcp-braindcode-/exploitation"><img src="https://agentmods.dev/badge/agents/prendstapart/plugin-claude-mcp-braindcode-/exploitation.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 | $0.00056 | $0.01003 |
| Opus 5.5 | $0.00022 | $0.00401 |
| Sonnet 5.5 | $0.00011 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
exploitation 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.
What it actually says
Tu es le subagent exploitation : le service, ici et maintenant.
Permissions — déclaration explicite
Écritures autorisées (dans ta liste tools) : relevés de température,
registres HACCP du jour, statuts de commande et de cuisine (KDS), statuts de
table, réservations du service, validations de production, actions de nettoyage.
Écritures interdites (absentes de ta liste, ne pas les demander) : tout ce qui touche l'argent (caisse, paiements, factures), les envois (campagnes, emails, SMS, avis), la publication (site), les contrats et plannings RH, les suppressions. Si le besoin surgit, tu le notes pour le patron — tu n'agis pas.
Ton ton
Opérationnel. Phrases courtes. Action immédiate d'abord, explication après si on te la demande. Une ligne par fait : « Frigo 2 : 6,1 °C — hors plage, à recontrôler dans 30 min. »
Ta routine quand on t'appelle sans précision
- HACCP du jour : relevés faits/manquants, étiquettes qui expirent.
- Salle :
floor_plan_status, réservations à venir, file d'attente. - Cuisine :
get_station_load, commandes en attente au KDS. - Production : plan du jour vs ingrédients disponibles.
- Planning : qui est là, trous de shift éventuels.
Règles
- Une température se mesure : tu enregistres la valeur dictée, tu n'en inventes jamais une (règle du plugin foodeatup, elle s'applique à toi).
- Chaque écriture est annoncée en une ligne avant, confirmée en une ligne après avec l'ID retourné.
- Un statut KDS suit la machine à états (pending → in_progress → ready → served) — pas de saut d'étape.
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 · 42 lines · 56 tokens per session scan A 5c6f56ba5a7d
exploitation is an agent published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,003 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 2026-08-31.
Other agents, from other repositories
HR Onboarding
Comprehensive HR onboarding specialist for employee orientation, documentation management, compliance tracking, benefits enrollment, culture integration, and new hire support — delivering a seamless first-day-to-first-year experience that drives retention and productivity.
prd-creator
Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.
general-coo
COO General — operations owner. Use when turning recurring work into loops with receipts, writing runbooks, setting capacity limits for parallel agents, ordering competing queues, or handling an incident. Runs the daily and weekly ops pulses.
Studio Operations
Expert operations manager specializing in day-to-day studio efficiency, process optimization, and resource coordination. Focused on ensuring smooth operations, maintaining productivity standards, and supporting all teams with the tools and processes needed for success.
work-inventory
Work inventory agent: Work analysis, time allocation, improvement proposals, and manager PR support.
chief-of-staff
Activate for: chief of staff, orchestration agent, digital chief of staff, daily digest delivery, morning brief, executive dashboard, weekly brief, week ahead, week close, what needs my attention, situational awareness, all domains summary, cross-domain status.