mako_help read
Return an ordered Mako workflow recipe for a task, with suggested arguments, batching hints, and verification steps.
When to use it
When the agent knows the task but not the right Mako tool sequence. This is the lowest-friction first call for new agents.
Input
{
"task": "audit route authorization before editing",
"focusFiles": ["app/dashboard/layout.tsx"],
"changedFiles": ["app/dashboard/layout.tsx"]
}context_packet read
Turn a messy coding request into ranked, source-labeled context using deterministic providers first. Modes tune the packet for exploration, planning, implementation, or review.
When to use it
The first call for any vague task. "debug auth onboarding", "where does X live?", "review impact of changing Y" — start here.
Input
{
"request": "debug why manager onboarding role checks are failing",
"focusFiles": ["lib/auth/dal.ts"], // optional
"mode": "implement",
"includeInstructions": true,
"includeRisks": true,
"risksMinConfidence": 0.7,
"includeLiveHints": true,
"freshnessPolicy": "prefer_fresh",
"budgetTokens": 4000
}Output (abridged)
{
"primaryContext": [{ "path": "...", "reason": "...", "score": 0.91 }, ...],
"relatedContext": [...],
"activeFindings": [...],
"risks": [...],
"modePolicy": {...},
"freshnessGate": {...},
"scopedInstructions": [...],
"recommendedHarnessPattern": "...",
"_hints": [...],
"expandableTools": ["route_trace", "db_rls", "reef_inspect"]
}Related
reef_scout for broader fact/finding scout. reef_inspect for one-file deep dive. See What is a context packet? for the full shape.
reef_scout read
Reef-backed scout packet of facts, findings, rules, and diagnostic candidates for a request.
When to use it
When the question is "what does Mako already know about
this?" rather than "what files are relevant?". Heavier on durable
Reef data than context_packet.
Input
{
"request": "audit auth boundaries before refactor",
"limit": 30
}Output
{
"facts": [...],
"findings": [...],
"rules": [...],
"diagnosticCandidates": [...]
}reef_diff_impact read
Diff-aware impact packet for files changed in the working tree. It reports changed-file overlay state, downstream callers, active findings on those callers, and convention risks.
When to use it
Mid-edit or just before review, especially when a change may invalidate facts on callers instead of only the edited files.
Input
{
"filePaths": ["lib/auth/dal.ts", "app/dashboard/layout.tsx"],
"depth": 2
}reef_inspect read
Explain one file or subject fingerprint with its facts, findings, and relevant diagnostic runs.
When to use it
Before editing a sensitive file. Returns the full evidence trail Reef has for that subject — what's known, what's questioned, what's been acked.
Input
{
"subjectKind": "file",
"subjectId": "lib/auth/dal.ts"
}evidence_confidence read
Label evidence as verified, fresh, stale, fuzzy, historical, contradicted, or unknown.
When to use it
When you've pulled a fact or finding and want to know whether you can trust it. Drives the freshness model — see How agentmako tracks freshness.
evidence_conflicts read
Find places where evidence sources disagree or where stale facts should be checked before an answer or edit.
tool_batch read
Run independent read-only Mako lookups in one labeled request. Reduces MCP round trips.
When to use it
When you want freshness, conventions, and open loops in one
call. tool_batch rejects mutation tools (no
project_index_refresh, working_tree_overlay,
diagnostic_refresh, db_reef_refresh,
finding_ack, or finding_ack_batch).
Input
{
"verbosity": "compact",
"continueOnError": true,
"ops": [
{ "label": "freshness", "tool": "project_index_status", "args": { "includeUnindexed": false } },
{ "label": "auth-conventions", "tool": "project_conventions", "args": { "limit": 20 } },
{ "label": "open-loops", "tool": "project_open_loops", "args": { "limit": 20 } }
]
}