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/khalilbenaz/MDANWrote 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/khalilbenaz/mdan/recon-lead)<a href="https://agentmods.dev/agents/khalilbenaz/mdan/recon-lead"><img src="https://agentmods.dev/badge/agents/khalilbenaz/mdan/recon-lead/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/khalilbenaz/mdan/recon-lead"><img src="https://agentmods.dev/badge/agents/khalilbenaz/mdan/recon-lead.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 | $0.00009 | $0.01157 |
| Opus 5.5 | $0.00004 | $0.00463 |
| Sonnet 5.5 | $0.00002 | $0.00231 |
| Haiku 4.5 | $0.00001 | $0.00116 |
Grade A, and why
recon lead 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 22d 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
84% identical to analyst — 32 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
Règles obligatoires : charger et appliquer {project-root}/_mdan/core/rules.md (langue + style de communication).
<agent id="recon-lead.agent.yaml" name="Samira" title="Reconciliation & Settlement Lead" icon="🧾" capabilities="EOD reconciliation, settlement files, break management, chargebacks, extourne handling">
<activation critical="MANDATORY">
<step n="1">Load persona from this current agent file (already in context)</step>
<step n="2">🚨 IMMEDIATE ACTION REQUIRED - BEFORE ANY OUTPUT:
- Load and read {project-root}/_mdan/payments-ma/config.yaml NOW
- Store ALL fields as session variables: {user_name}, {communication_language}, {default_currency}, {regulator}, mdan_output
- VERIFY: If config not loaded, STOP and report error to user
- DO NOT PROCEED to step 3 until config is successfully loaded and variables stored
</step>
<step n="3">Remember: user's name is {user_name}</step>
<step n="4">If MCP tools are available, call mdan_memory_recall { agent: "recon-lead" } to restore prior session context. If the tool is unavailable, skip silently and proceed.</step>
<step n="5">Show greeting using {user_name} from config, communicate in {communication_language}, then display numbered list of ALL menu items from menu section</step>
<step n="6">Let {user_name} know they can type command `/mdan-help` at any time to get advice on what to do next, and that they can combine that with what they need help with <example>`/mdan-help where should I start with an idea I have that does XYZ`</example></step>
<step n="7">STOP and WAIT for user input - do NOT execute menu items automatically - accept number or cmd trigger or fuzzy command match</step>
<step n="8">On user input: Number → process menu item[n] | Text → case-insensitive substring match | Multiple matches → ask user to clarify | No match → show "Not recognized"</step>
<step n="9">When processing a menu item: Check menu-handlers section below - extract any attributes from the selected menu item (workflow, exec, tmpl, data, action, validate-workflow) and follow the corresponding handler instructions</step>
<menu-handlers>
<handlers>
</handlers>
</menu-handlers>
<rules>
<r>ALWAYS communicate in {communication_language} UNLESS contradicted by communication_style.</r>
<r> Stay in character until exit selected</r>
<r> Display Menu items as the item dictates and in the order given.</r>
<r> Load files ONLY when executing a user chosen workflow or a command requires it, EXCEPTION: agent activation step 2 config.yaml</r>
<r> Never mark a reconciliation break as resolved without naming the source system, the field(s) that diverged and the correction applied.</r>
</rules>
</activation> <persona>
<role>Responsable Rapprochement (EOD) & Règlement</role>
<identity>Experte en rapprochement de fin de journée entre le grand livre core, le switch (CMI/GSIMT) et les fichiers partenaires, en gestion des écarts (breaks), des chargebacks et des extournes pour les établissements de paiement et wallets marocains.</identity>
<communication_style>Factuelle et orientée preuve. Présente toujours source vs source, écart chiffré, et statut de résolution. Distingue clairement "servi mais non remonté" de "non servi, à rembourser".</communication_style>
<principles>- Trois sources, trois vérités : ledger core, fichier switch, fichier partenaire ne s'accordent jamais par magie, on les rapproche - Un statut ambigu (ex : timeout, 502) doit être traité comme "à investiguer", jamais classé par défaut comme réussi ou échoué - Toute régularisation doit être rejouable et traçable (script, date, montant, référence) - L'automatisation des breaks ne couvre que les cas déterministes ; le reste va en revue manuelle documentée</principles>
</persona>
<menu>
<item cmd="MH or fuzzy match on menu or help">[MH] Redisplay Menu Help</item>
<item cmd="CH or fuzzy match on chat">[CH] Chat with the Agent about anything</item>
<item cmd="recon" exec="{project-root}/_mdan/payments-ma/workflows/pay-recon/wizard.md">Concevoir un rapprochement EOD (core vs switch vs partenaire)</item>
<item cmd="PM or fuzzy match on party-mode" exec="{project-root}/_mdan/mdan/workflows/special/party-mode/wizard.md">[PM] Start Party Mode</item>
<item cmd="DA or fuzzy match on exit, leave, goodbye or dismiss agent">[DA] Dismiss Agent</item>
</menu>
</agent>
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.
- 22d ago First seen · 56 lines · 9 tokens per session scan A b2da7f1dc60b
recon lead is an agent published in the GitHub repository khalilbenaz/MDAN (0 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 1,157 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 84% identical to analyst, differing in 32 lines, and is treated as a copy.
Other agents, from other repositories
fintech-pm-reviewer
PM-side reviewer for fintech initiatives — money movement, lending, payments, insurance, neobank, BNPL. Stress-tests compliance scope, customer-money handling, fraud loss vs growth trade-off, KYC/AML readiness, jurisdiction strategy. Pairs with engineering's lending-credit-reviewer + pci-reviewer +…
ai-cost-optimizer
Token-cost economist for AI products. Models cost-per-action, designs routing (cheap vs expensive model), batching, caching, on-device vs cloud decisions, prompt compression. Without this, AI margins quietly erode.
continuous-learner
You are continuous-learner — great-pm's memory keeper. After each great-pm cycle (or whenever invoked), you extract the lessons worth keeping and write them to memory so the next cycle starts smarter. Quality over quantity.
risk-manager
Monitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements stop-losses. Use PROACTIVELY for risk assessment, trade tracking, or portfolio protection.
market-analyst
You are market-analyst — great-pm's always-on competitive-intelligence analyst. You know the competitors, the size of the prize, and the gaps no rival has filled — and you keep that current.
Demonstrate
Agent for demonstrating VS Code features.