@inetafrica/open-claudia 2.6.59 → 2.7.1

package/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## v2.7.1
+- **The system prompt now teaches tool-FIRST, not tool-after (enforcement 5d).** The fixed "Reusable tools" section in `core/system-prompt.js` was the root cause of the baseline failure: it taught "crystallise the script you just wrote" — do the work raw, save a tool afterwards. Rewritten as "Tools are the interface": before operational work, walk the loop **search → use (read TOOL.md first, never guess args) → extend the missing verb → scaffold first** — and only then do the work *through* the tool. Raw one-liners and heredocs are demoted to probing/diagnosis; a broken tool gets fixed or journaled (`tool note --issue`), never routed around. The section also documents the risk gate honestly: the `--yes`/`--yes-destructive` flag is the agent's mechanical acknowledgment *after* the user approves — it never replaces asking first.
+- **Tool-scout: operational turns can no longer meet silence (enforcement 5a).** Today an empty tool match is silent, and silence reads as permission to improvise. The discoverer now runs a pattern-based scout (no LLM, ~zero cost) over each seeds/full-tier turn: a table of high-precision operational domains — named hosts (central.inet.africa, ticket-central, chat-central, git.coders.africa…), prod IP ranges, infra commands (kubectl, argocd, mongosh…) — each with a `covers` matcher against the tool registry. When a turn trips a domain: if a registry tool covers it but wasn't auto-surfaced, the block points at it by name (`tool show X`, then work through it); if **nothing** covers it, the block says so and hands over the exact scaffold command (`tool scaffold <suggested-name> --risk write`). Domains already covered by a surfaced tool stay quiet, and non-operational chatter never trips the patterns (precision over recall — they expand from audit evidence later, per 5c). Gap signals flow into recall metrics (`toolGaps`) and the engine result for future `/tooltrace` surfacing. Extends `test-recall-discoverer.js` with pure-function and through-the-engine scout coverage.
+
+## v2.7.0
+- **Tools become memory objects (tool-first architecture, Phase 1).** A tool is no longer a flat script — it's a directory: `tools/<name>/tool` (the executable), `TOOL.md` (Interface · Known issues · State · Journal — the curated, human-readable condition of the tool), and `state.json` (machine telemetry, runtime-written, gitignored). The tools dir is now a **git repository**: every add, metadata change, note, and removal auto-commits (with a per-invocation identity, never touching git config), so `git log` *is* the upgrade history and any change is one revert from undone. `tool show` is tiered disclosure: header metadata, live telemetry, TOOL.md, and the recent commit log — the source only with `--source`, so reading about a tool no longer costs its whole body in context.
+- **Risk tiers + run gate.** Every tool declares `risk: read-only | write | destructive` in its header (absent = treated as write, fail-safe). `tool run` now enforces the ask-first rule mechanically: read-only runs freely; write requires `--yes`; destructive requires `--yes-destructive` — and a plain `--yes` does **not** unlock a destructive tool. Refusals exit 3 with a clear message. The flags pass through to the tool unstripped, so tools with their own confirmation gates (e.g. prod-k8s) keep working. `tool add`/`tool set` accept `--risk`; adding without it defaults to write and says so.
+- **Run telemetry stamped at the point of use.** `tool run` itself records every execution into the tool's `state.json`: run count, last used, last exit, last success/failure, per-verb health (first non-flag arg), and a rolling history of the last 20 invocations with timing. A failing run prints a nudge to journal the defect (`tool note <name> --issue "..."`). This is the v1.2 health doctrine in code: no smoke tests, no health crons — health is verified by use, and breakage is captured automatically where it happens.
+- **`tool scaffold`, `tool note`, `tool migrate`.** `scaffold <name>` creates a ready-to-extend verb-dispatch stub (node or bash) with full header, TOOL.md skeleton, and initial telemetry — and refuses if the tool exists ("extend it instead"). `note <name> --issue|--state|--journal` maintains TOOL.md from the CLI: issues and journal lines insert newest-first; `--state` rewrites the State section (it describes *now*, not history). `migrate` converts legacy flat-file tools into directories — one commit each, sidecar telemetry carried over, TOOL.md generated — and runs automatically on first CLI use, so existing tools arrive in the new layout with their memory intact.
+- **Secrets can no longer be saved into a tool.** The add-time secret lint is now **blocking** (was advisory): `tool add`, `tool set`, and `tool note` refuse content matching credential patterns, because the git-backed dir would remember the secret forever. Other lints (requires mismatch, syntax check, dangling pack) stay advisory. Extends `test-tools.js` end to end: layout, risk gate matrix, per-verb telemetry, secret refusal, migration, scaffold, git history.
+
 ## v2.6.58
 - **Tiered recall gate — stop paying 15 seconds for "thanks".** Measured over 700+ live turns, the old discoverer pre-gate returned true whenever *any* seed matched, so it gated just 0.4% of turns — a bare "ok" with an incidental keyword hit still paid the full seed → graph → walker pass (p50 ~15s). A new `recallTier()` classifies each turn into three tiers: **skip** (pleasantries/acks up to 4 words *regardless of seeds*, emoji-only, or ≤2 words with no seeds — no recall at all), **seeds** (short command-like turns ≤4 words — user-origin keyword seeds inject directly with no graph expansion, no walker, no excerpts; the classic-engine baseline at ~ms cost), and **full** (substantive turns — the whole pipeline). The tier is logged per turn and the metrics summary now tracks the seeds-only share alongside the gated share.
 - **Walker candidate cap.** The latency deep-dive showed the walk itself dominates, not process spawn: 15–40 candidates × 600-char excerpts = 10–25KB prompts to the haiku judge on every substantive turn. Full-tier candidates are now priority-ordered — user-origin seeds by match score, then context seeds, then graph-activated nodes by activation — and capped at `RECALL_WALKER_MAX_CANDIDATES` (default 14), so the judge reads the strongest few instead of everything the graph touched.

package/bin/cli.js

@@ -374,7 +374,7 @@ Memory tools:
   open-claudia transcript-window <pattern>   Search project transcript, show hits with context
                                              (alias: tw; --help for options)
   open-claudia pack list|show|match|archive|restore|archived  Context packs: living topic docs (skills + memory)
-  open-claudia tool list|search|show|add|set|edit|run|remove Reusable tools: executable scripts the agent saves & re-runs (keyring preauth)
+  open-claudia tool list|search|show|scaffold|add|set|note|edit|run|migrate|remove  Reusable tools: git-tracked dirs (exec + TOOL.md + telemetry), risk-gated runs
   open-claudia entity list|show|match|note   Entity notes: people/places/projects memory
   open-claudia lessons list|add|remove|show  Always-loaded learned rules (cross-cutting, promoted after a miss)
   open-claudia ideas list|add|remove|show    Self-improvement backlog (captured by the nightly dream)

package/bin/tool.js

@@ -1,23 +1,38 @@
-// CLI: manage and run reusable tools — executable scripts the agent saves so a
-// procedure it worked out once becomes a re-runnable command, not a re-typed
-// heredoc. The executable sibling of context packs (`open-claudia pack`).
+// CLI: manage and run reusable tools — the interface operational work happens
+// through. Tool-first loop: search → exists: use it → missing a verb: extend →
+// nothing: scaffold, then work through the tool.
 //
 //   open-claudia tool list                       — index (name — description [skill])
 //   open-claudia tool search <query>             — lexical match (find before adding a dup)
-//   open-claudia tool show <name>                — full docs, path, keyring status
-//   open-claudia tool add <path> [--name n]      — register a script as a tool
-//       [--pack <dir>] [--desc "..."] [--requires "k1,k2"] [--usage "..."]
+//   open-claudia tool show <name> [--source]     — TOOL.md, telemetry, history (source with --source)
+//   open-claudia tool scaffold <name>            — create a new tool skeleton (dir + stub + TOOL.md)
+//       [--pack <dir>] [--desc "..."] [--risk read-only|write|destructive]
+//       [--requires "k1,k2"] [--usage "..."] [--lang node|bash]
+//   open-claudia tool add <path> [--name n]      — register an existing script as a tool
+//       [--pack <dir>] [--desc "..."] [--risk tier] [--requires "k1,k2"] [--usage "..."]
 //   open-claudia tool set <name> [--desc ...]    — fix a tool's metadata in place
-//       [--pack <dir>] [--requires "k1,k2"] [--usage "..."]
+//       [--pack <dir>] [--risk tier] [--requires "k1,k2"] [--usage "..."]
+//   open-claudia tool note <name>                — append to TOOL.md (auto-committed)
+//       [--issue "..."] [--state "..."] [--journal "..."]
 //   open-claudia tool edit <name>                — print the file path to open & edit
-//   open-claudia tool run <name> [args...]       — run it with keyring pre-loaded
+//   open-claudia tool run <name> [args...]       — run it (keyring pre-loaded, risk-gated)
+//   open-claudia tool migrate                    — convert legacy flat-file tools to directories
 //   open-claudia tool remove <name>              — delete one
 //   open-claudia tool path                       — print the tools directory
 //
-// Fix before fork: when a tool is wrong, prefer `tool set` (metadata) or `tool
-// edit` (open the file) over adding a near-duplicate. `add` lints the source on
-// save — flags hardcoded secrets, requires/keyring mismatches, syntax errors,
-// and dangling pack links — all advisory, never blocking.
+// A tool is a directory: executable + TOOL.md (Interface · Known issues ·
+// State · Journal) + state.json (runtime telemetry). The dir is git-tracked;
+// every change commits, so `git -C $(open-claudia tool path) log` is the
+// upgrade history.
+//
+// Risk tiers gate `tool run`: write-tier needs --yes, destructive-tier needs
+// --yes-destructive — get the user's approval first; the flag records that
+// deliberate step. Read-only tools run freely.
+//
+// Fix before fork: when a tool is wrong, prefer `tool set` (metadata), `tool
+// note` (docs), or `tool edit` (body) over adding a near-duplicate. Hardcoded
+// secrets BLOCK a save; other lints (requires/keyring mismatch, syntax,
+// dangling pack link) stay advisory.
 //
 // Credentials: a tool runs with the operational keyring merged into its env, so
 // reference creds as $NAME inside the script. `open-claudia keyring list` shows
@@ -25,6 +40,7 @@
 
 const { spawnSync } = require("child_process");
 const tools = require("../core/tools");
+const repo = require("../core/tool-repo");
 
 // Minimal flag parser: pulls --key value (and --key=value) out of argv, returns
 // { positional, flags }.
@@ -88,6 +104,17 @@ function run(args) {
   const cmd = (args[0] || "list").toLowerCase();
   const rest = args.slice(1);
 
+  // Auto-migrate legacy flat-file tools to the directory layout on first use
+  // (idempotent, one git commit per tool, telemetry carried over).
+  if (cmd !== "path") {
+    try {
+      if (repo.hasLegacyTools()) {
+        const { migrated } = repo.migrateLegacyTools();
+        if (migrated.length) console.error(`(migrated ${migrated.length} tool(s) to directory layout: ${migrated.join(", ")})`);
+      }
+    } catch (e) { /* best-effort */ }
+  }
+
   switch (cmd) {
     case "list":
     case "ls": {
@@ -98,7 +125,8 @@ function run(args) {
       console.log(`${all.length} reusable tool(s) — run via 'open-claudia tool run <name>':\n`);
       for (const t of all) {
         const skill = t.pack ? `  [skill: ${t.pack}]` : "";
-        console.log(`• ${t.name} — ${t.description || "(no description)"}${skill}`);
+        const risk = t.risk === "read-only" ? "" : `  [${t.risk || "write?"}]`;
+        console.log(`• ${t.name} — ${t.description || "(no description)"}${skill}${risk}`);
       }
       console.log(`\nDocs: open-claudia tool show <name>   ·   Dir: ${tools.TOOLS_DIR}`);
       break;
@@ -125,13 +153,15 @@ function run(args) {
 
     case "show":
     case "cat": {
-      const name = rest[0];
-      if (!name) { console.error("Usage: tool show <name>"); process.exitCode = 1; return; }
+      const { positional, flags } = parseFlags(rest);
+      const name = positional[0];
+      if (!name) { console.error("Usage: tool show <name> [--source]"); process.exitCode = 1; return; }
       const t = tools.findTool(name);
       if (!t) { console.error(`No tool named "${name}". Run: open-claudia tool list`); process.exitCode = 1; return; }
       console.log(`Tool: ${t.name}`);
       if (t.description) console.log(`Description: ${t.description}`);
       if (t.pack) console.log(`Skill pack: ${t.pack}  (open-claudia pack show ${t.pack})`);
+      console.log(`Risk: ${t.risk || "(undeclared — treated as write)"}`);
       console.log(`Usage: open-claudia tool run ${t.name}${t.usage ? "   (" + t.usage + ")" : ""}`);
       if (t.requires.length) {
         const missing = tools.missingRequires(t);
@@ -139,6 +169,22 @@ function run(args) {
         console.log(`Requires keyring keys: ${t.requires.join(", ")}  (${status})`);
       }
       console.log(`File: ${t.file}${t.executable ? "" : "  (not executable!)"}`);
+
+      // Telemetry: overall + per-verb health from state.json.
+      if (t.runCount || t.lastUsed) {
+        const exit = t.lastExit === undefined ? "" : ` · last exit ${t.lastExit}`;
+        console.log(`Runs: ${t.runCount}${t.lastUsed ? ` · last used ${t.lastUsed.slice(0, 16).replace("T", " ")}` : ""}${exit}`);
+      }
+      if (t.verbs && Object.keys(t.verbs).length) {
+        const rows = Object.entries(t.verbs).map(([v, s]) =>
+          `  • ${v}: ${s.runs} run(s), last exit ${s.lastExit}${s.lastSuccess ? `, last success ${s.lastSuccess.slice(0, 10)}` : ""}`);
+        console.log("Verbs:\n" + rows.join("\n"));
+      }
+      try {
+        const log = repo.toolLog(t.name, 5);
+        if (log.length) console.log("Recent changes:\n" + log.map((l) => "  " + l).join("\n"));
+      } catch (e) { /* git optional */ }
+
       // Directed tool-graph: what tends to run right after / before this one.
       try {
         const graph = require("../core/tool-graph");
@@ -156,7 +202,13 @@ function run(args) {
           }
         }
       } catch (e) { /* graph optional (old node) */ }
-      console.log(`\n----- source -----\n${t.content}`);
+
+      // Tiered disclosure: TOOL.md is the manual; source only when modifying.
+      const doc = tools.readToolDoc(t.name);
+      if (doc) console.log(`\n----- TOOL.md -----\n${doc.trim()}`);
+      if (flags.source) console.log(`\n----- source -----\n${t.content}`);
+      else if (!doc) console.log(`\n----- source (no TOOL.md yet) -----\n${t.content}`);
+      else console.log(`\n(source: open-claudia tool show ${t.name} --source)`);
       break;
     }
 
@@ -173,10 +225,14 @@ function run(args) {
           name: typeof flags.name === "string" ? flags.name : undefined,
           pack: typeof flags.pack === "string" ? flags.pack : undefined,
           description: typeof flags.desc === "string" ? flags.desc : (typeof flags.description === "string" ? flags.description : undefined),
+          risk: typeof flags.risk === "string" ? flags.risk : undefined,
           requires: typeof flags.requires === "string" ? flags.requires.split(/[,\s]+/).filter(Boolean) : undefined,
           usage: typeof flags.usage === "string" ? flags.usage : undefined,
         });
-        console.log(`Saved tool "${t.name}"${t.pack ? ` (skill: ${t.pack})` : ""}.`);
+        console.log(`Saved tool "${t.name}"${t.pack ? ` (skill: ${t.pack})` : ""} — risk: ${t.risk}.`);
+        if (t.defaultedRisk) {
+          console.log(`  No --risk given → defaulted to "write" (runs will demand --yes). If it only reads, fix: open-claudia tool set ${t.name} --risk read-only`);
+        }
         console.log(`Run it: open-claudia tool run ${t.name}`);
         if (t.requires.length) {
           const missing = tools.missingRequires(t);
@@ -217,17 +273,21 @@ function run(args) {
       if (typeof flags.desc === "string") patch.description = flags.desc;
       else if (typeof flags.description === "string") patch.description = flags.description;
       if (typeof flags.pack === "string") patch.pack = flags.pack;
+      if (typeof flags.risk === "string") patch.risk = flags.risk;
       if (typeof flags.requires === "string") patch.requires = flags.requires.split(/[,\s]+/).filter(Boolean);
       if (typeof flags.usage === "string") patch.usage = flags.usage;
       if (Object.keys(patch).length === 0) {
-        console.error('Nothing to set. Pass at least one of --desc / --pack / --requires / --usage. Body edits: open-claudia tool edit ' + name);
+        console.error('Nothing to set. Pass at least one of --desc / --pack / --risk / --requires / --usage. Body edits: open-claudia tool edit ' + name);
         process.exitCode = 1; return;
       }
-      const updated = tools.updateToolHeader(name, patch);
+      let updated;
+      try { updated = tools.updateToolHeader(name, patch); }
+      catch (e) { console.error(`Could not update "${name}": ${e.message}`); process.exitCode = 1; return; }
       if (!updated) { console.error(`Could not update "${name}".`); process.exitCode = 1; return; }
       console.log(`Updated tool "${updated.name}".`);
       console.log(`  Description: ${updated.description || "(none)"}`);
       if (updated.pack) console.log(`  Skill pack:  ${updated.pack}`);
+      console.log(`  Risk:        ${updated.risk || "(undeclared — treated as write)"}`);
       if (updated.requires.length) console.log(`  Requires:    ${updated.requires.join(", ")}`);
       if (updated.usage) console.log(`  Usage:       ${updated.usage}`);
       reportSafety(updated);
@@ -252,14 +312,108 @@ function run(args) {
       if (!name) { console.error("Usage: tool run <name> [args...]"); process.exitCode = 1; return; }
       const t = tools.findTool(name);
       if (!t) { console.error(`No tool named "${name}". Run: open-claudia tool list`); process.exitCode = 1; return; }
+      const toolArgs = rest.slice(1);
+
+      // Risk-tier gate: write needs --yes, destructive needs --yes-destructive.
+      // The flag is passed through to the tool (which may have its own gate).
+      const gate = tools.runGate(t, toolArgs);
+      if (!gate.ok) { console.error(gate.message); process.exitCode = 3; return; }
+
       const missing = tools.missingRequires(t);
       if (missing.length) {
         console.error(`Cannot run ${t.name}: missing keyring keys ${missing.join(", ")}. Set them with 'open-claudia keyring set <name> <value>'.`);
         process.exitCode = 1; return;
       }
-      const r = spawnSync(t.file, rest.slice(1), { stdio: "inherit", env: tools.runEnv() });
-      if (r.error) { console.error(`Failed to run ${t.name}: ${r.error.message}`); process.exitCode = 1; return; }
-      process.exitCode = typeof r.status === "number" ? r.status : 1;
+      const started = Date.now();
+      const r = spawnSync(t.file, toolArgs, { stdio: "inherit", env: tools.runEnv() });
+      const ms = Date.now() - started;
+      if (r.error) {
+        tools.recordRunResult(t.name, { args: toolArgs, exit: -1, ms });
+        console.error(`Failed to run ${t.name}: ${r.error.message}`);
+        process.exitCode = 1; return;
+      }
+      const exit = typeof r.status === "number" ? r.status : 1;
+      tools.recordRunResult(t.name, { args: toolArgs, exit, ms });
+      if (exit !== 0) {
+        console.error(`(exit ${exit} recorded in ${t.name} telemetry — if this is a real defect, journal it: ` +
+          `open-claudia tool note ${t.name} --issue "<what broke>")`);
+      }
+      process.exitCode = exit;
+      break;
+    }
+
+    case "scaffold":
+    case "new": {
+      const { positional, flags } = parseFlags(rest);
+      const name = positional[0];
+      if (!name) {
+        console.error('Usage: tool scaffold <name> [--pack dir] [--desc "..."] [--risk read-only|write|destructive] [--requires "k1,k2"] [--usage "..."] [--lang node|bash]');
+        process.exitCode = 1; return;
+      }
+      try {
+        const t = repo.scaffoldTool(name, {
+          pack: typeof flags.pack === "string" ? flags.pack : undefined,
+          description: typeof flags.desc === "string" ? flags.desc : (typeof flags.description === "string" ? flags.description : undefined),
+          risk: typeof flags.risk === "string" ? flags.risk : undefined,
+          requires: typeof flags.requires === "string" ? flags.requires.split(/[,\s]+/).filter(Boolean) : [],
+          usage: typeof flags.usage === "string" ? flags.usage : undefined,
+          lang: typeof flags.lang === "string" ? flags.lang : "node",
+        });
+        console.log(`Scaffolded tool "${t.name}" (risk: ${t.risk}).`);
+        console.log(`  Executable: ${t.file}`);
+        console.log(`  Docs:       ${t.docFile}`);
+        console.log(`Fill in the verbs, then work through it: open-claudia tool run ${t.name} <verb>`);
+      } catch (e) {
+        console.error(`Could not scaffold: ${e.message}`); process.exitCode = 1;
+      }
+      break;
+    }
+
+    case "note": {
+      const { positional, flags } = parseFlags(rest);
+      const name = positional[0];
+      const issue = typeof flags.issue === "string" ? flags.issue : null;
+      const state = typeof flags.state === "string" ? flags.state : null;
+      const journal = typeof flags.journal === "string" ? flags.journal : null;
+      if (!name || (!issue && !state && !journal)) {
+        console.error('Usage: tool note <name> [--issue "..."] [--state "..."] [--journal "..."]');
+        process.exitCode = 1; return;
+      }
+      const t = tools.findTool(name);
+      if (!t) { console.error(`No tool named "${name}". Run: open-claudia tool list`); process.exitCode = 1; return; }
+      if (!t.docFile) { console.error(`"${t.name}" is a legacy flat tool — run any tool command to migrate it first.`); process.exitCode = 1; return; }
+      try {
+        tools.assertNoSecrets([issue, state, journal].filter(Boolean).join("\n"), "note");
+        const fs = require("fs");
+        let doc = tools.readToolDoc(t.name) || repo.toolMdSkeleton(t);
+        const date = new Date().toISOString().slice(0, 10);
+        const appendUnder = (heading, line) => {
+          const re = new RegExp(`(##\\s*${heading}[^\\n]*\\n)`, "i");
+          if (re.test(doc)) doc = doc.replace(re, `$1${line}\n`);
+          else doc += `\n## ${heading}\n${line}\n`;
+        };
+        if (issue) appendUnder("Known issues", `- [${date}] ${issue}`);
+        if (state) {
+          // State is a rewrite, not an append — it describes NOW.
+          const re = /(##\s*State[^\n]*\n)([\s\S]*?)(?=\n##\s|$)/i;
+          if (re.test(doc)) doc = doc.replace(re, `$1${state}\n\n`);
+          else doc += `\n## State\n${state}\n`;
+        }
+        if (journal) appendUnder("Journal", `- [${date}] ${journal}`);
+        fs.writeFileSync(t.docFile, doc, { mode: 0o600 });
+        repo.commitTool(t.name, `note ${t.name}: ${(issue || state || journal).slice(0, 60)}`);
+        console.log(`Noted in ${t.name}/TOOL.md${issue ? " (known issue)" : ""}${state ? " (state)" : ""}${journal ? " (journal)" : ""}.`);
+      } catch (e) {
+        console.error(`Could not note: ${e.message}`); process.exitCode = 1;
+      }
+      break;
+    }
+
+    case "migrate": {
+      const { migrated, skipped } = repo.migrateLegacyTools();
+      if (!migrated.length && !skipped.length) console.log("Nothing to migrate — all tools already use the directory layout.");
+      if (migrated.length) console.log(`Migrated: ${migrated.join(", ")}`);
+      if (skipped.length) console.log(`Skipped (no tool header — left untouched): ${skipped.join(", ")}`);
       break;
     }
 
@@ -277,7 +431,7 @@ function run(args) {
       break;
 
     default:
-      console.log('Usage: open-claudia tool [list | search <query> | show <name> | add <path> [flags] | set <name> [flags] | edit <name> | run <name> [args] | remove <name> | path]');
+      console.log('Usage: open-claudia tool [list | search <query> | show <name> [--source] | scaffold <name> [flags] | add <path> [flags] | set <name> [flags] | note <name> [flags] | edit <name> | run <name> [args] | migrate | remove <name> | path]');
   }
 }
 

package/core/recall/discoverer.js

@@ -27,6 +27,65 @@ const toolsLib = require("../tools");
 // entity-only). Optional — absent on old node where node:sqlite is missing.
 let toolGraph = null;
 try { toolGraph = require("../tool-graph"); } catch (e) { /* old node */ }
+
+// ── Tool-scout (enforcement 5a): operational-domain gap detection ────────────
+// When a turn looks operational, an empty tool match must not stay silent —
+// silence reads as permission to improvise a raw script. v1 is pure patterns,
+// no LLM: `test` decides the turn touches an operational domain (named hosts,
+// prod IPs, infra commands — precision over recall so local/dev chatter never
+// trips it); `covers` finds a registry tool that fronts that domain (matched
+// on name + description); `slug` is the suggested scaffold name when nothing
+// in the registry covers it. Patterns expand from audit evidence (5c).
+const OPERATIONAL_DOMAINS = [
+  { label: "Kubernetes cluster ops", test: /\bkubectl\b|\bargocd\b|control[- ]plane|\brollout (?:status|restart|history)\b/i, covers: /k8s|kubernetes|kubectl|cluster/i, slug: "prod-k8s" },
+  { label: "in-cluster MongoDB", test: /\bmongosh\b|\bmongo\b[^\n]*--eval|\bdb\.\w+\.(?:find|update\w*|delete\w*|insert\w*|aggregate)\(/i, covers: /mongo|k8s/i, slug: "prod-k8s" },
+  { label: "inet-central platform API", test: /central\.inet\.africa|\binet[- ]central\b/i, covers: /inet[- ]?central/i, slug: "inet-central-cli" },
+  { label: "ticket-central API", test: /ticketcentral|\bticket[- ]central\b/i, covers: /\bticket/i, slug: "kticket" },
+  { label: "kazee chat-central API", test: /\bchat[- ]central\b/i, covers: /kazee-chat|chat/i, slug: "kchat" },
+  { label: "kazee spaces API", test: /spaces\.kazee|\bspaces[- ]central\b/i, covers: /spaces/i, slug: "spaces" },
+  { label: "GitLab / coders.africa", test: /git\.coders\.africa|codersafrica@|\bgitlab\b/i, covers: /gitlab|coders/i, slug: "gitlab-ops" },
+  { label: "MikroTik / RouterOS", test: /mikrotik|routeros|winbox|\/rest\/(?:ip|ppp|queue)\b/i, covers: /mikrotik|routeros/i, slug: "mikrotik" },
+  { label: "iNet radius/ops backend", test: /radius\.inet\.africa|ops\.inet\.africa/i, covers: /radius|pppoe/i, slug: "inet-radius" },
+  { label: "production network host", test: /\b10\.200\.\d{1,3}\.\d{1,3}\b|\b102\.222\.4\.\d{1,3}\b/, covers: null, slug: "" },
+];
+
+// Pure + exported for tests. Returns [{ label, kind: "use", tool }] when a
+// registry tool covers a tripped domain but was not surfaced this turn, or
+// [{ label, kind: "scaffold", slug }] when nothing in the registry covers it.
+// Domains already covered by a surfaced (kept) tool produce no signal.
+function scoutToolGaps(userText, keptToolNames, allTools) {
+  const text = String(userText || "");
+  if (!text) return [];
+  let all = allTools;
+  if (!all) { try { all = toolsLib.listTools(); } catch (e) { return []; } }
+  const kept = [...(keptToolNames || [])].map((n) => String(n).toLowerCase());
+  const gaps = [];
+  const seen = new Set();
+  for (const d of OPERATIONAL_DOMAINS) {
+    if (!d.test.test(text)) continue;
+    if (d.covers && kept.some((n) => d.covers.test(n))) continue;
+    const hit = d.covers
+      ? all.find((t) => d.covers.test(t.name) || d.covers.test(String(t.description || "")))
+      : null;
+    if (hit && kept.includes(hit.name.toLowerCase())) continue;
+    const g = hit
+      ? { label: d.label, kind: "use", tool: hit.name }
+      : { label: d.label, kind: "scaffold", slug: d.slug || "" };
+    const key = g.kind + ":" + (g.tool || g.slug || g.label);
+    if (seen.has(key)) continue;
+    seen.add(key);
+    gaps.push(g);
+  }
+  return gaps;
+}
+
+function renderToolGaps(gaps) {
+  if (!gaps || !gaps.length) return "";
+  const lines = gaps.map((g) => g.kind === "use"
+    ? `- ${g.label}: covered by existing tool \`${g.tool}\` (not auto-surfaced this turn) — \`open-claudia tool show ${g.tool}\`, then work through it.`
+    : `- ${g.label}: NO tool covers this domain. Scaffold before improvising: \`open-claudia tool scaffold ${g.slug || "<system-name>"} --desc "<what it fronts>" --risk write\` — implement the verb you need, then do the work through it.`);
+  return `\n\n## Tool-first check (operational turn)\nThis turn touches operational domains. Do the operational work THROUGH a tool — raw one-liners only to probe:\n${lines.join("\n")}\n`;
+}
 // Episodic memory: FTS over past transcripts (same optionality as the graphs).
 let transcriptIndex = null;
 try { transcriptIndex = require("../transcript-index"); } catch (e) { /* old node */ }
@@ -236,7 +295,7 @@ async function run(ctx) {
   const tier = recallTier(userText, seedCount);
   if (tier === "skip") {
     metrics.logTurn({ engine: "discoverer", model: WALKER_MODEL, query: userText, gated: true, tier, latencyMs: Date.now() - started });
-    return { packBlock: "", entityBlock: "", toolBlock: "", episodeBlock: "", packMatches: [], entityMatches: [], toolMatches: [], episodeMatches: [], why: {}, gated: true, tier };
+    return { packBlock: "", entityBlock: "", toolBlock: "", episodeBlock: "", packMatches: [], entityMatches: [], toolMatches: [], toolGaps: [], episodeMatches: [], why: {}, gated: true, tier };
   }
 
   // 3: spreading activation from seeds across the graph (full tier only — the
@@ -464,6 +523,14 @@ async function run(ctx) {
     toolBlock = `\n\n## Tools that may help here\nSurfaced for this turn — run with \`open-claudia tool run <name> [args]\`; read docs/source with \`open-claudia tool show <name>\`:\n${lines.join("\n")}\n`;
   }
 
+  // 5a tool-scout: replace the silence of an empty/partial tool match with an
+  // explicit use-this-tool or scaffold-first signal on operational turns. Runs
+  // on both seeds and full tiers (short command-like turns are exactly the
+  // operational ones); skip-tier pleasantries never reach here.
+  let toolGaps = [];
+  try { toolGaps = scoutToolGaps(userText, toolMatches.map((m) => m.name)); } catch (e) {}
+  if (toolGaps.length) toolBlock += renderToolGaps(toolGaps);
+
   // Past-conversation episodes the walker kept (fail-open drops them — an
   // unjudged transcript snippet is a guess, not a memory).
   const episodeMatches = episodeCands
@@ -497,12 +564,13 @@ async function run(ctx) {
     walkerMs: walkRes.walkerMs,
     walker: walkRes.source,
     costUsd: walkRes.costUsd || 0,
+    toolGaps: toolGaps.length ? toolGaps.map((g) => `${g.kind}:${g.tool || g.slug || g.label}`) : undefined,
   });
 
   return {
     packBlock, entityBlock, toolBlock, episodeBlock, packMatches: finalPacks, entityMatches: finalEnts,
-    toolMatches, episodeMatches, why: whyMap ? Object.fromEntries(whyMap) : {}, gated: false, tier,
+    toolMatches, toolGaps, episodeMatches, why: whyMap ? Object.fromEntries(whyMap) : {}, gated: false, tier,
   };
 }
 
-module.exports = { name: "discoverer", run, needsRecall, recallTier, walk, cascadeVerdict };
+module.exports = { name: "discoverer", run, needsRecall, recallTier, walk, cascadeVerdict, scoutToolGaps, renderToolGaps };

package/core/system-prompt.js

@@ -79,18 +79,25 @@ function buildToolIndexBlock() {
     if (count) {
       listing = `\nYou have ${count} reusable tool${count === 1 ? "" : "s"}. The ones relevant to a turn are surfaced automatically below (\"Tools that may help here\"). To find others on demand: \`open-claudia tool search <query>\` (lexical match) or \`open-claudia tool list\`; read docs/source with \`open-claudia tool show <name>\`; run with \`open-claudia tool run <name> [args]\`.\n`;
     } else {
-      listing = "\nNo reusable tools saved yet — the first time you work out how to hit an API or drive an interface, save it as one.\n";
+      listing = "\nNo reusable tools exist yet — your first operational task starts by scaffolding the tool for it, not by improvising a script.\n";
     }
   } catch (e) {
     return "";
   }
-  return `\n## Reusable tools (build skills as you work)
-When you work out how to do something operational — hit an API, drive an interface, transform a file, run a multi-step flow — do NOT leave it as a throwaway heredoc. Crystallise it into a reusable tool so next time it's a single command, not a re-derivation. This is a core behaviour, not an optional extra: prefer saving a tool over re-typing a script you've written before.
+  return `\n## Tools are the interface (tool-first)
+Operational work — hitting an API, mutating a live system, driving an interface, any command you would re-derive next time — happens THROUGH a reusable tool, not around one. BEFORE doing the work, walk this loop in order:
 
-- A tool is one executable file (any language; shebang picks the interpreter) with a parseable comment header. Save the script you just wrote with \`open-claudia tool add <path> --pack <skill-dir> --desc "..." [--requires "key1,key2"] [--usage "..."]\`. The \`--pack\` link ties it to the matching skill pack so the prose how-to and the runnable how-to stay together.
-- Preauth: tools run with the operational keyring merged into their environment — and so does your OWN Bash, right now. Every operational credential is already present as an environment variable in your shell and in any tool you run; reference it as \`$inet_central_user\` etc. instead of asking for it or hardcoding it. Run \`open-claudia keyring list\` to see the exact names available. In a saved tool, declare what it needs via \`--requires\` so a missing key is reported before the run, and never write a secret into the file.
-- Read a tool's docs and source on demand with \`open-claudia tool show <name>\` (don't guess its args). Full CLI: \`open-claudia tool list|show|add|run|remove\`.
-- When a tool's behaviour changes or you improve it, update the saved tool rather than forking a new heredoc. Announce in one line when you create or change a tool, same as packs.
+1. **Search** — check the "Tools that may help here" block if present; otherwise \`open-claudia tool search <query>\` or \`tool list\`.
+2. **Use** — a tool covers it: read it first (\`open-claudia tool show <name>\` gives docs, State, known issues, recent changes — never guess its args; \`--source\` only when modifying), then \`open-claudia tool run <name> <verb> [args]\`.
+3. **Extend** — right tool, missing verb: add the verb to that tool (\`tool edit <name>\`, then \`tool note <name> --journal "added <verb>"\`) and run it. One CLI per system, verbs as subcommands — never fork a near-duplicate.
+4. **Scaffold** — no tool fronts the system: \`open-claudia tool scaffold <name> --desc "..." --risk <read-only|write|destructive> [--pack <dir>] [--requires "key1,key2"]\` FIRST, implement the verb you need, then do the work through it.
+
+Raw shell one-liners and heredocs are for probing and diagnosis only — never the operational action itself. If a tool is broken, fix it or journal the defect (\`tool note <name> --issue "..."\`); do not route around it with a script.
+
+- Risk gate: read-only tools run freely; write-tier needs \`--yes\`; destructive needs \`--yes-destructive\`. The flag is your mechanical acknowledgment AFTER the user approves the action — it never replaces asking first.
+- Tools carry their own memory: TOOL.md (Interface · Known issues · State · Journal) is the manual, state.json records every run (per-verb health), and every change is a git commit. Keep TOOL.md truthful as you work; update the tool in place when behaviour changes.
+- Preauth: the operational keyring is merged into tool runs — and into your own Bash. Reference creds as \`$inet_central_user\` etc. (\`open-claudia keyring list\` shows names); declare a tool's needs via \`--requires\` so a missing key reports before the run; never write a secret into a tool file (saves are refused).
+- Announce in one line when you scaffold or change a tool, same as packs. Full CLI: \`open-claudia tool list|search|show|scaffold|add|set|note|edit|run|migrate|remove\`.
 ${listing}`;
 }