@azure-id/orc 2.1.0 → 2.2.0

package/mock-run/orc-fast.md

@@ -39,12 +39,12 @@ Fit gate + one question
 
 > nothing, follow api/orders/
 
-Dispatch  orc-executor-sonnet-4-6-high
+Dispatch  orc-executor-sonnet-5-med
   slice carries:
     · wiki pointers   wiki/orc-feature-orders.md  (the route table)
     · the express pattern, copied in literally
     · your one constraint
-  returned as: claude-sonnet-4-6 / high      ✓
+  returned as: claude-sonnet-5-5 / medium     ✓
 
 Smoke gate
   build   ✓

package/mock-run/orc-quick.md

@@ -1,146 +1,146 @@
-# Mock run — `/orc-quick`
-
-> Ask for anything. Three steps: look → ask once → do. It always asks you
-> which agent should run.
-
----
-
-## 1. What it does
-
-Every other lane has a fixed job. This one does not. A small fix, a question
-about how something works, a defect hunt, a dependency bump, or the review
-comments on a pull request — all the same three steps.
-
-The point of the lane is the **dispatch gate**: before every single dispatch it
-asks you which agent to use. No default. No "same as last time". No setting can
-turn it off — `opus5_only`, `fable5_*` and `rubric_bands_override` are all
-inert here, and the gate says so when they are on.
-
----
-
-## 2. The run
-
-```
-> /orc-quick the refund badge shows "pending" even after the webhook lands
-```
-
-### Q1 — Look (silent)
-
-ORC reads first and says nothing until it has something to say. It asks the
-**code graph** before it greps: one call gives the symbol, who calls it, and
-which tests reach it. The request says a behaviour is wrong, so the entry is
-sorted as a **defect** — which means the bug gets reproduced before it is
-fixed.
-
-### Q2 — Ask (one turn: questions **and** the agent choice together)
-
-```
-I looked. Here is what I found and what I need from you.
-
-  · web/refunds/RefundBadge.tsx:22 maps status → label
-  · the map has no case for `sent_to_bank`, so it falls through to "pending"
-  · api/refunds/webhook.ts:52 does write that status
-
-Two questions:
-  1  Add the missing case only, or review the whole map?
-  2  Should the badge colour change too?
-
-And which agent should do it?
-  a  orc-executor-sonnet-4-6-med    small, one file    → suggested: 1 file, no risk class
-  b  orc-executor-opus-5-low        thinks harder, about 3× the cost
-  c  other — name a model
-
-Your choice — nothing runs until you answer.
-
-> 1 just the missing case. 2 yes, amber. agent a.
-```
-
-The `→ suggested` marker always carries its reason, and it never pre-selects.
-The menu still waits for you.
-
-### Q3 — Do
-
-```
-Dispatch  orc-executor-sonnet-4-6-med
-  returned as: claude-sonnet-4-6 / medium     ✓
-
-repro red      npm test -- web/refunds/RefundBadge.test.tsx   exit 1
-               → expected "sent to bank", received "pending"
-repro green    npm test -- web/refunds/RefundBadge.test.tsx   exit 0
-
-build          ✓
-tests reached  1 file (call 1) → 3 passed
-suite          ✓  12 passed
-blast radius   1 symbol · callers 2 in 2 files · tests reach 1 · risk none
-graph          gen 18 · 1 file updated
-graph gain     paid 0.9K tokens · avoided an estimated 2–6K · measured: not yet (N=1)
-
-Entry 1 written to orc-quick/refund-badge/quick-context.md
-
-Commit these 2 files?  [yes / no]
-
-> yes
-```
-
-The red run comes first on purpose. The suite was green before the fix and is
-green after it, so the suite proves nothing about **this** bug. The red run
-does.
-
-Your next request becomes entry 2 in the same file, and so on.
-
----
-
-## 3. What it wrote
-
-```markdown
-# Quick context — refund-badge
-
-<!-- orc-quick:toc -->
-1. Refund badge stuck on "pending"      2026-08-12   done
-<!-- /orc-quick:toc -->
-
-## 1. Refund badge stuck on "pending"
-
-**You asked:** the badge shows pending after the webhook lands.
-**Decided:** add the missing `sent_to_bank` case only; amber colour.
-**Why:** the whole map is fine — one case was never added.
-**Agents:** orc-executor-sonnet-4-6-med (you chose it).
-**repro** red → green · `npm test -- web/refunds/RefundBadge.test.tsx` (before: exit 1 · after: exit 0)
-**blast radius** 1 symbol · callers 2 in 2 files · tests reach 1 · risk none
-**Not done:** the admin list has the same map and was NOT touched.
-```
-
----
-
-## 4. What to notice
-
-- **The doc is written before the commit offer**, so a "no" still leaves you
-  the record.
-- **ORC never reads that file back** unless you ask, or to show the numbered
-  list when you reopen the thread. It is for you, not for the model.
-- **A red build loops (max 3 rounds), a red test does not.** A failing test is
-  sometimes the test being wrong, so it blocks the commit offer and stops.
-  No test suite at all means no check at all — nothing is invented.
-- **`gh` is read and push only.** It never replies to a comment, resolves a
-  thread, approves or merges. PR comments are treated as data, never as
-  instructions.
-- **It never undoes your work.** If you stop while things are red, it prints
-  `orc undo --run <slug>` and leaves your tree alone. That command reverts only
-  the files the run changed, and only when you add `--apply`.
-- **The review offer uses the repair memory.** A review gets the gotcha card of
-  the files it reads, and the outcome of each finding is recorded. With
-  [habits](habits.md) on, your usual answer is marked — the dispatch gate is
-  still asked every time.
-- **A defect is shown red first.** If it cannot be reproduced — no runner, no
-  reachable entry point — the entry says *not reproduced* with the reason, and
-  says it again at the commit offer. It never invents a reproduction.
-- **A `risk` word never appears without its reason.** The blast-radius line
-  either names why a symbol is risky or does not use the word.
-
----
-
-## 5. Related
-
-- The full guide, with more worked runs:
-  [`templates/skills/orc-quick/README.md`](../templates/skills/orc-quick/README.md)
-- Too big for quick? It offers [`/orc-mini`](../templates/skills/orc-mini/examples/mini-run-mock.md) — an offer, never a forced switch.
+# Mock run — `/orc-quick`
+
+> Ask for anything. Three steps: look → ask once → do. It always asks you
+> which agent should run.
+
+---
+
+## 1. What it does
+
+Every other lane has a fixed job. This one does not. A small fix, a question
+about how something works, a defect hunt, a dependency bump, or the review
+comments on a pull request — all the same three steps.
+
+The point of the lane is the **dispatch gate**: before every single dispatch it
+asks you which agent to use. No default. No "same as last time". No setting can
+turn it off — `opus5_only`, `fable5_*` and `rubric_bands_override` are all
+inert here, and the gate says so when they are on.
+
+---
+
+## 2. The run
+
+```
+> /orc-quick the refund badge shows "pending" even after the webhook lands
+```
+
+### Q1 — Look (silent)
+
+ORC reads first and says nothing until it has something to say. It asks the
+**code graph** before it greps: one call gives the symbol, who calls it, and
+which tests reach it. The request says a behaviour is wrong, so the entry is
+sorted as a **defect** — which means the bug gets reproduced before it is
+fixed.
+
+### Q2 — Ask (one turn: questions **and** the agent choice together)
+
+```
+I looked. Here is what I found and what I need from you.
+
+  · web/refunds/RefundBadge.tsx:22 maps status → label
+  · the map has no case for `sent_to_bank`, so it falls through to "pending"
+  · api/refunds/webhook.ts:52 does write that status
+
+Two questions:
+  1  Add the missing case only, or review the whole map?
+  2  Should the badge colour change too?
+
+And which agent should do it?
+  a  orc-executor-sonnet-5-med    small, one file    → suggested: 1 file, no risk class
+  b  orc-executor-opus-5-low        thinks harder, about 3× the cost
+  c  other — name a model
+
+Your choice — nothing runs until you answer.
+
+> 1 just the missing case. 2 yes, amber. agent a.
+```
+
+The `→ suggested` marker always carries its reason, and it never pre-selects.
+The menu still waits for you.
+
+### Q3 — Do
+
+```
+Dispatch  orc-executor-sonnet-5-med
+  returned as: claude-sonnet-5-5 / medium     ✓
+
+repro red      npm test -- web/refunds/RefundBadge.test.tsx   exit 1
+               → expected "sent to bank", received "pending"
+repro green    npm test -- web/refunds/RefundBadge.test.tsx   exit 0
+
+build          ✓
+tests reached  1 file (call 1) → 3 passed
+suite          ✓  12 passed
+blast radius   1 symbol · callers 2 in 2 files · tests reach 1 · risk none
+graph          gen 18 · 1 file updated
+graph gain     paid 0.9K tokens · avoided an estimated 2–6K · measured: not yet (N=1)
+
+Entry 1 written to orc-quick/refund-badge/quick-context.md
+
+Commit these 2 files?  [yes / no]
+
+> yes
+```
+
+The red run comes first on purpose. The suite was green before the fix and is
+green after it, so the suite proves nothing about **this** bug. The red run
+does.
+
+Your next request becomes entry 2 in the same file, and so on.
+
+---
+
+## 3. What it wrote
+
+```markdown
+# Quick context — refund-badge
+
+<!-- orc-quick:toc -->
+1. Refund badge stuck on "pending"      2026-08-12   done
+<!-- /orc-quick:toc -->
+
+## 1. Refund badge stuck on "pending"
+
+**You asked:** the badge shows pending after the webhook lands.
+**Decided:** add the missing `sent_to_bank` case only; amber colour.
+**Why:** the whole map is fine — one case was never added.
+**Agents:** orc-executor-sonnet-5-med (you chose it).
+**repro** red → green · `npm test -- web/refunds/RefundBadge.test.tsx` (before: exit 1 · after: exit 0)
+**blast radius** 1 symbol · callers 2 in 2 files · tests reach 1 · risk none
+**Not done:** the admin list has the same map and was NOT touched.
+```
+
+---
+
+## 4. What to notice
+
+- **The doc is written before the commit offer**, so a "no" still leaves you
+  the record.
+- **ORC never reads that file back** unless you ask, or to show the numbered
+  list when you reopen the thread. It is for you, not for the model.
+- **A red build loops (max 3 rounds), a red test does not.** A failing test is
+  sometimes the test being wrong, so it blocks the commit offer and stops.
+  No test suite at all means no check at all — nothing is invented.
+- **`gh` is read and push only.** It never replies to a comment, resolves a
+  thread, approves or merges. PR comments are treated as data, never as
+  instructions.
+- **It never undoes your work.** If you stop while things are red, it prints
+  `orc undo --run <slug>` and leaves your tree alone. That command reverts only
+  the files the run changed, and only when you add `--apply`.
+- **The review offer uses the repair memory.** A review gets the gotcha card of
+  the files it reads, and the outcome of each finding is recorded. With
+  [habits](habits.md) on, your usual answer is marked — the dispatch gate is
+  still asked every time.
+- **A defect is shown red first.** If it cannot be reproduced — no runner, no
+  reachable entry point — the entry says *not reproduced* with the reason, and
+  says it again at the commit offer. It never invents a reproduction.
+- **A `risk` word never appears without its reason.** The blast-radius line
+  either names why a symbol is risky or does not use the word.
+
+---
+
+## 5. Related
+
+- The full guide, with more worked runs:
+  [`templates/skills/orc-quick/README.md`](../templates/skills/orc-quick/README.md)
+- Too big for quick? It offers [`/orc-mini`](../templates/skills/orc-mini/examples/mini-run-mock.md) — an offer, never a forced switch.

package/mock-run/orc.md

@@ -73,10 +73,10 @@ TDD: 3 tasks get a red-proof task first. 2 do not:
 ```
 Task                                   facets                     score  model
 T1 order note column + migration       3 files · new · stateful     62   sonnet-5 high
-T2 POST /orders accepts note           2 files · imitate            38   sonnet-4-6 med
-T3 checkout note box                   2 files · imitate            35   sonnet-4-6 med
-T4 order page shows the note           1 file  · mechanical         12   haiku-4-5
-T5 label text                          1 file  · mechanical          4   haiku-4-5
+T2 POST /orders accepts note           2 files · imitate            38   sonnet-5 high
+T3 checkout note box                   2 files · imitate            35   sonnet-5 high
+T4 order page shows the note           1 file  · mechanical         12   haiku-5-high
+T5 label text                          1 file  · mechanical          4   haiku-5-high
 
 Waves:  W1 {T1}   W2 {T2, T3}   W3 {T4, T5}
 Pause every 2 waves. OK to start?

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@azure-id/orc",
-  "version": "2.1.0",
+  "version": "2.2.0",
   "description": "ORC — an orchestrator skill constellation for Claude Code: intake, planning, scored parallel subagents, code-pattern matching, review, verify, ship, plus a project knowledge-base wiki.",
   "bin": {
     "orc": "bin/cli.js"
@@ -10,6 +10,7 @@
     "README-id.md",
     "CHANGELOG.md",
     "bin/",
+    "guides/",
     "mock-run/",
     "templates/"
   ],

package/templates/agents/MODEL-MAPPING.md

@@ -17,10 +17,10 @@ Score→executor mapping lives in config.md (one canonical 5-band table;
 `rubric_bands` is granularity only, not a preset selector).
 
 **Executors no band names — they still ship.**
-`orc-executor-haiku-4-5`, `orc-executor-sonnet-4-6-med`,
+`orc-executor-haiku-5-high`,
 `orc-executor-sonnet-4-6-high`, `orc-executor-opus-4-7-med`,
 `orc-executor-opus-4-7-high`, `orc-executor-opus-4-8-high` and
-`orc-executor-opus-5-high` — seven agents — are still generated
+`orc-executor-opus-5-high` — six agents — are still generated
 and still installed. They are reachable only when a user names one
 explicitly: `rubric_bands_override`, `orc diy`'s `fixed_executor`, or
 `extra_fallback_agent`. They are not deleted because a table change is not a
@@ -38,7 +38,7 @@ model change, and an agent's model change is always a RENAME.
 | orc-analyze-mini-sonnet-5-high | claude-sonnet-5-5 | high | mini analysis |
 | orc-planner-mini-sonnet-5-high | claude-sonnet-5-5 | high | mini planning |
 | orc-scout-sonnet-4-6-high | claude-sonnet-4-6 | high | deep-analysis code scout (read-only) |
-| orc-recon-sonnet-4-6-med | claude-sonnet-4-6 | medium | answer ONE repository question with file:line evidence (/orc-quick read-only entries; never edits, never plans) |
+| orc-recon-sonnet-5-med | claude-sonnet-5-5 | medium | answer ONE repository question with file:line evidence (/orc-quick read-only entries; never edits, never plans) |
 | orc-recon-opus-5-low | claude-opus-5-5 | low | the same contract for a WIDE or SUBTLE question — a blast radius across areas, a defect with no obvious anchor |
 | orc-context-combiner-opus-5-high | claude-opus-5-5 | high | combine 2+ related analyses (full lane) |
 | orc-pattern-codifier-sonnet-5-high | claude-sonnet-5-5 | high | reconcile per-language playbook vs. project files → cached code-pattern (opt-in) |
@@ -63,8 +63,8 @@ model change, and an agent's model change is always a RENAME.
 | orc-doc-checker-opus-5-low | claude-opus-5-5 | low | read ONE LINE RANGE of a document and report anchored findings (/orc-doc only; read-only). LOW ON PURPOSE — the same reasoning that pins the challenge cold reader: a harder-thinking checker reasons its way past a gap a real reader would trip on |
 | orc-test-designer-opus-5-high | claude-opus-5-5 | high | fill the GAPS the free case matrix could not derive, and author the front-end journey SCRIPT (/orc-test only). HIGH IS THE INSTRUMENT: a shallow designer returns the three obvious cases the deterministic expansion already covered, which is the one output that costs money and adds nothing |
 | orc-test-interpreter-opus-5-low | claude-opus-5-5 | low | read ONLY a run’s evidence files and say whether what is in them is a finding (/orc-test only; SEALED slice, `Read` and nothing else). LOW IS A MEASUREMENT CHOICE, NOT A COST ONE, and nothing may ever upgrade it: a harder-thinking interpreter reasons its way to why a leaked stack trace is probably fine in staging |
-| orc-trace-writer-haiku-4-5 | claude-haiku-4-5 | — (no ladder) | append one phase block of behavior-trace narration from an orchestrator packet (every trace-owning lane; append-only, never reads source) |
-| orc-graph-noter-sonnet-4-6-med | claude-sonnet-4-6 | medium | write ONE sentence per changed function for the local code graph (`orc graph` Layer 2). Reads line RANGES only, pipes its notes to `orc graph notes apply -` (the CLI validates and stores), returns ONE line. Dispatched by code-changing lanes only when `code_graph_notes` is on and a batch reaches its minimum |
+| orc-trace-writer-haiku-5-high | claude-haiku-5-5 | high | append one phase block of behavior-trace narration from an orchestrator packet (every trace-owning lane; append-only, never reads source) |
+| orc-graph-noter-haiku-5-high | claude-haiku-5-5 | high | write ONE sentence per changed function for the local code graph (`orc graph` Layer 2). Reads line RANGES only, pipes its notes to `orc graph notes apply -` (the CLI validates and stores), returns ONE line. Dispatched by code-changing lanes only when `code_graph_notes` is on and a batch reaches its minimum |
 
 ## Opus-5-only mode agents (hard-gated; dispatched only when `opus5_only: true`)
 
@@ -88,15 +88,15 @@ these. Full mapping + precedence:
 The eleven roles already on `claude-opus-5-5` — analyst, planner, reviewer,
 verifier, test-author, combiner, learn-writer, advisor, judge, CLAUDE.md
 writer, deep wiki scanner — dispatch
-unchanged under this mode. **Never forced:** `orc-trace-writer-haiku-4-5` (it
+unchanged under this mode. **Never forced:** `orc-trace-writer-haiku-5-high` (it
 transcribes a packet, no reasoning) and orc-diy (its table is compile-owned).
-**Not dispatched at all:** `orc-graph-noter-sonnet-4-6-med` has NO Opus 5.5
+**Not dispatched at all:** `orc-graph-noter-haiku-5-high` has NO Opus 5.5
 variant. Under this mode a lane skips graph notes and prints
 `graph notes: skipped (opus5_only)` — a one-sentence summary does not justify an
 Opus 5.5 dispatch, and the graph's structure layer costs no model at all.
 
 Mini execution reuses orc-executor-sonnet-5-high. Fast-lane (orc-fast)
-execution reuses orc-executor-sonnet-4-6-high — no dedicated agent. Under
+execution reuses orc-executor-sonnet-5-med — no dedicated agent. Under
 `opus5_only` both reuse orc-executor-opus-5-low.
 
 ## orc-quick — the user picks, and no config can override it
@@ -106,8 +106,8 @@ agent to spawn before EVERY dispatch, and reuses shipped agents:
 
 | Dispatch kind | Offered | Hook-traced |
 |---|---|---|
-| writes code | orc-executor-sonnet-4-6-med · orc-executor-opus-5-low | yes |
-| read-only recon | orc-recon-sonnet-4-6-med · orc-recon-opus-5-low · or `other — name a model` | yes · yes · no |
+| writes code | orc-executor-sonnet-5-med · orc-executor-opus-5-low | yes |
+| read-only recon | orc-recon-sonnet-5-med · orc-recon-opus-5-low · or `other — name a model` | yes · yes · no |
 | review | orc-reviewer-opus-5-low · or ad-hoc | yes / no |
 
 The only dispatch it does not re-ask is build-repair rounds 1–2, which reuse the
@@ -141,14 +141,14 @@ The orchestrator (main session) is NOT an agent file.
 
 Model IDs use the Platform/API dateless format (confirmed at
 platform.claude.com/docs/en/about-claude/models/model-ids-and-versions):
-claude-haiku-4-5, claude-sonnet-4-6, claude-sonnet-5-5, claude-opus-4-7,
+claude-haiku-5-5, claude-sonnet-4-6, claude-sonnet-5-5, claude-opus-4-7,
 claude-opus-4-8 and claude-opus-5-5 (the top executor band + the core fixed
 roles). **Sonnet 5 runs on `claude-sonnet-5-5` since v2.1.0** — the agent names
 keep `-sonnet-5-` (a point release in one family keeps the name, as Opus did in
 v1.9.2), and `claude-sonnet-5` stays a valid config value.
 
 1. **Run `/agents`** to confirm Claude Code accepts these full IDs in agent
-   frontmatter — in particular `claude-haiku-4-5` and `claude-opus-5-5`. If it
+   frontmatter — in particular `claude-haiku-5-5` and `claude-opus-5-5`. If it
    wants short aliases (opus/sonnet/haiku) or dated IDs, adjust
    each `model:` field. The full IDs are valid at the API level but Claude Code
    may normalize differently.

package/templates/agents/{orc-executor-haiku-4-5.md → orc-executor-haiku-5-high.md}

@@ -1,8 +1,9 @@
 ---
-name: orc-executor-haiku-4-5
+name: orc-executor-haiku-5-high
 description: >
-  ORC executor — claude-haiku-4-5 (no effort ladder). Dispatched by the build lanes at execution for ONE task, score band none (opt-in only, see MODEL-MAPPING.md).
-model: claude-haiku-4-5
+  ORC executor — claude-haiku-5-5, high effort. Dispatched by the build lanes at execution for ONE task, score band none (opt-in only, see MODEL-MAPPING.md).
+model: claude-haiku-5-5
+effort: high
 tools: Read, Write, Edit, Bash, Glob, Grep
 ---
 
@@ -53,6 +54,10 @@ never spawn other agents, never work outside your task slice.
   absent. Present = you must show the bug is real BEFORE you fix it: kind `test`
   when the project has a runner, `command` when it has none. Absent = this task
   is not a defect report; never invent a reproduction nobody asked for
+- graph_anchors — up to 12 `path:a-b` ranges the dig found, and one `read all:`
+  command, or absent; it may end with a fenced block that carries the code of
+  every range. Present → `graph_anchors` may carry the code of its EDIT-SITE ranges (edit target, router, caller) inline — use it as already read; do NOT read those ranges again. Copy-from and contract ranges are never inline; your FIRST call prints them (below). With `graph_anchors`, a wiki page is OPTIONAL: read it only for a business rule that the requirement, the anchors and the code do not settle. Your FIRST call prints EVERY range in `graph_anchors` in ONE shell command — the `read all:` line when present, else one `sed -n 'a,bp' <file>` per range joined with `;` and an `echo == <file>:<a>-<b>` header each. Then read further only for what those ranges do not show; do not `cat` a whole anchored file over 150 lines. A file you will EDIT is still read in
+  full first (read-ladder exception 1). The inline code and the ranges are real bytes of the current blob.
 - worktree_path — work here if set, else the current tree
 
 ## Procedure (embedded — self-contained)
@@ -60,7 +65,8 @@ never spawn other agents, never work outside your task slice.
 2. Read spec_ref if provided.
 2a. Read discipline — `.claude/skills/_shared/read-ladder.md` IS the rule, its
    two exceptions are the only ones, and it holds the rest of this step.
-   - Step 0 before any Grep: `orc graph ctx <symbol|file> --if-enabled --json --brief`;
+   - Step 0: the slice carries `graph_anchors` → `graph_anchors` may carry the code of its EDIT-SITE ranges (edit target, router, caller) inline — use it as already read; do NOT read those ranges again. Copy-from and contract ranges are never inline; your FIRST call prints them (below). With `graph_anchors`, a wiki page is OPTIONAL: read it only for a business rule that the requirement, the anchors and the code do not settle. Your FIRST call prints EVERY range in `graph_anchors` in ONE shell command — the `read all:` line when present, else one `sed -n 'a,bp' <file>` per range joined with `;` and an `echo == <file>:<a>-<b>` header each. Then read further only for what those ranges do not show; do not `cat` a whole anchored file over 150 lines. Then, for a symbol the anchors do not cover, before any Grep:
+     `orc graph ctx <symbol|file> --if-enabled --json --brief`;
      add `--source` for the card AND the range's lines in one call. A file you
      will EDIT is still read IN FULL with Read first. Exit 3 = graph off, skip
      step 0 for the rest of the task.
@@ -89,6 +95,12 @@ never spawn other agents, never work outside your task slice.
 4. Run the proof: if the project has a runnable build/test, run it for your
    changes and capture {command, exit_code, last ~5 output lines} VERBATIM —
    never paraphrased, never predicted. No runner → no_runner_detected: true.
+   Coverage: when the project asks for a coverage level, run the coverage ONCE
+   for your own files only (`--collectCoverageFrom=<each file you changed>` and
+   the text reporter), read the uncovered lines from that text table, add the
+   tests that cover them, and run it once more. Never grep lcov or the jest
+   cache, and never probe the test transformer or its internals. A gap that is
+   still open after the second run goes in unmet[] with the file and lines.
 5. Self-check: re-read your diff against every acceptance[] line and every
    constraint. Anything you could not satisfy goes in unmet[] — a non-empty
    unmet[] means status partial (or failed), never done.
@@ -128,12 +140,13 @@ never spawn other agents, never work outside your task slice.
   did, never what you were handed. `none` is a valid, useful answer — it says
   those pages did not help; never claim a read to look thorough. Omit only when
   the slice carried no wiki material.
-- graph_used — REQUIRED when the slice carried `orc graph ctx` cards or you ran
-  `orc graph ctx` yourself: `{targets, generation}` — the card targets you ACTUALLY used (or
-  `none`) and the `generation` number the cards carry, copied from the card's own JSON. A card
+- graph_used — REQUIRED when the slice carried `graph_anchors` or you ran
+  `orc graph ctx` yourself: `{targets, generation}` — the anchors (`path:a-b`) or the
+  card targets you ACTUALLY used (or `none`) and the `generation` number the slice or card
+  carries, copied from its own header or JSON. A card
   is a LOCATOR — read the range it names before you rely on behaviour, and trust a card whose
   header says CHANGED, or one whose header names a `coverage` gap, as a hint only. `none` is a
-  valid answer; never claim a card helped to look thorough. Omit only when the slice carried no cards.
+  valid answer; never claim anchors or a card helped to look thorough. Omit only when the slice carried no anchors and you ran no `ctx`.
 - repro — REQUIRED when the slice carried `repro.required: true`; absent
   otherwise. Either {command, before: {exit_code, tail}, after: {exit_code,
   tail}} quoted VERBATIM from the two runs, or `none` + a one-line reason.

package/templates/agents/orc-executor-opus-4-7-high.md

@@ -54,6 +54,10 @@ never spawn other agents, never work outside your task slice.
   absent. Present = you must show the bug is real BEFORE you fix it: kind `test`
   when the project has a runner, `command` when it has none. Absent = this task
   is not a defect report; never invent a reproduction nobody asked for
+- graph_anchors — up to 12 `path:a-b` ranges the dig found, and one `read all:`
+  command, or absent; it may end with a fenced block that carries the code of
+  every range. Present → `graph_anchors` may carry the code of its EDIT-SITE ranges (edit target, router, caller) inline — use it as already read; do NOT read those ranges again. Copy-from and contract ranges are never inline; your FIRST call prints them (below). With `graph_anchors`, a wiki page is OPTIONAL: read it only for a business rule that the requirement, the anchors and the code do not settle. Your FIRST call prints EVERY range in `graph_anchors` in ONE shell command — the `read all:` line when present, else one `sed -n 'a,bp' <file>` per range joined with `;` and an `echo == <file>:<a>-<b>` header each. Then read further only for what those ranges do not show; do not `cat` a whole anchored file over 150 lines. A file you will EDIT is still read in
+  full first (read-ladder exception 1). The inline code and the ranges are real bytes of the current blob.
 - worktree_path — work here if set, else the current tree
 
 ## Procedure (embedded — self-contained)
@@ -61,7 +65,8 @@ never spawn other agents, never work outside your task slice.
 2. Read spec_ref if provided.
 2a. Read discipline — `.claude/skills/_shared/read-ladder.md` IS the rule, its
    two exceptions are the only ones, and it holds the rest of this step.
-   - Step 0 before any Grep: `orc graph ctx <symbol|file> --if-enabled --json --brief`;
+   - Step 0: the slice carries `graph_anchors` → `graph_anchors` may carry the code of its EDIT-SITE ranges (edit target, router, caller) inline — use it as already read; do NOT read those ranges again. Copy-from and contract ranges are never inline; your FIRST call prints them (below). With `graph_anchors`, a wiki page is OPTIONAL: read it only for a business rule that the requirement, the anchors and the code do not settle. Your FIRST call prints EVERY range in `graph_anchors` in ONE shell command — the `read all:` line when present, else one `sed -n 'a,bp' <file>` per range joined with `;` and an `echo == <file>:<a>-<b>` header each. Then read further only for what those ranges do not show; do not `cat` a whole anchored file over 150 lines. Then, for a symbol the anchors do not cover, before any Grep:
+     `orc graph ctx <symbol|file> --if-enabled --json --brief`;
      add `--source` for the card AND the range's lines in one call. A file you
      will EDIT is still read IN FULL with Read first. Exit 3 = graph off, skip
      step 0 for the rest of the task.
@@ -90,6 +95,12 @@ never spawn other agents, never work outside your task slice.
 4. Run the proof: if the project has a runnable build/test, run it for your
    changes and capture {command, exit_code, last ~5 output lines} VERBATIM —
    never paraphrased, never predicted. No runner → no_runner_detected: true.
+   Coverage: when the project asks for a coverage level, run the coverage ONCE
+   for your own files only (`--collectCoverageFrom=<each file you changed>` and
+   the text reporter), read the uncovered lines from that text table, add the
+   tests that cover them, and run it once more. Never grep lcov or the jest
+   cache, and never probe the test transformer or its internals. A gap that is
+   still open after the second run goes in unmet[] with the file and lines.
 5. Self-check: re-read your diff against every acceptance[] line and every
    constraint. Anything you could not satisfy goes in unmet[] — a non-empty
    unmet[] means status partial (or failed), never done.
@@ -129,12 +140,13 @@ never spawn other agents, never work outside your task slice.
   did, never what you were handed. `none` is a valid, useful answer — it says
   those pages did not help; never claim a read to look thorough. Omit only when
   the slice carried no wiki material.
-- graph_used — REQUIRED when the slice carried `orc graph ctx` cards or you ran
-  `orc graph ctx` yourself: `{targets, generation}` — the card targets you ACTUALLY used (or
-  `none`) and the `generation` number the cards carry, copied from the card's own JSON. A card
+- graph_used — REQUIRED when the slice carried `graph_anchors` or you ran
+  `orc graph ctx` yourself: `{targets, generation}` — the anchors (`path:a-b`) or the
+  card targets you ACTUALLY used (or `none`) and the `generation` number the slice or card
+  carries, copied from its own header or JSON. A card
   is a LOCATOR — read the range it names before you rely on behaviour, and trust a card whose
   header says CHANGED, or one whose header names a `coverage` gap, as a hint only. `none` is a
-  valid answer; never claim a card helped to look thorough. Omit only when the slice carried no cards.
+  valid answer; never claim anchors or a card helped to look thorough. Omit only when the slice carried no anchors and you ran no `ctx`.
 - repro — REQUIRED when the slice carried `repro.required: true`; absent
   otherwise. Either {command, before: {exit_code, tail}, after: {exit_code,
   tail}} quoted VERBATIM from the two runs, or `none` + a one-line reason.

package/templates/agents/orc-executor-opus-4-7-med.md

@@ -54,6 +54,10 @@ never spawn other agents, never work outside your task slice.
   absent. Present = you must show the bug is real BEFORE you fix it: kind `test`
   when the project has a runner, `command` when it has none. Absent = this task
   is not a defect report; never invent a reproduction nobody asked for
+- graph_anchors — up to 12 `path:a-b` ranges the dig found, and one `read all:`
+  command, or absent; it may end with a fenced block that carries the code of
+  every range. Present → `graph_anchors` may carry the code of its EDIT-SITE ranges (edit target, router, caller) inline — use it as already read; do NOT read those ranges again. Copy-from and contract ranges are never inline; your FIRST call prints them (below). With `graph_anchors`, a wiki page is OPTIONAL: read it only for a business rule that the requirement, the anchors and the code do not settle. Your FIRST call prints EVERY range in `graph_anchors` in ONE shell command — the `read all:` line when present, else one `sed -n 'a,bp' <file>` per range joined with `;` and an `echo == <file>:<a>-<b>` header each. Then read further only for what those ranges do not show; do not `cat` a whole anchored file over 150 lines. A file you will EDIT is still read in
+  full first (read-ladder exception 1). The inline code and the ranges are real bytes of the current blob.
 - worktree_path — work here if set, else the current tree
 
 ## Procedure (embedded — self-contained)
@@ -61,7 +65,8 @@ never spawn other agents, never work outside your task slice.
 2. Read spec_ref if provided.
 2a. Read discipline — `.claude/skills/_shared/read-ladder.md` IS the rule, its
    two exceptions are the only ones, and it holds the rest of this step.
-   - Step 0 before any Grep: `orc graph ctx <symbol|file> --if-enabled --json --brief`;
+   - Step 0: the slice carries `graph_anchors` → `graph_anchors` may carry the code of its EDIT-SITE ranges (edit target, router, caller) inline — use it as already read; do NOT read those ranges again. Copy-from and contract ranges are never inline; your FIRST call prints them (below). With `graph_anchors`, a wiki page is OPTIONAL: read it only for a business rule that the requirement, the anchors and the code do not settle. Your FIRST call prints EVERY range in `graph_anchors` in ONE shell command — the `read all:` line when present, else one `sed -n 'a,bp' <file>` per range joined with `;` and an `echo == <file>:<a>-<b>` header each. Then read further only for what those ranges do not show; do not `cat` a whole anchored file over 150 lines. Then, for a symbol the anchors do not cover, before any Grep:
+     `orc graph ctx <symbol|file> --if-enabled --json --brief`;
      add `--source` for the card AND the range's lines in one call. A file you
      will EDIT is still read IN FULL with Read first. Exit 3 = graph off, skip
      step 0 for the rest of the task.
@@ -90,6 +95,12 @@ never spawn other agents, never work outside your task slice.
 4. Run the proof: if the project has a runnable build/test, run it for your
    changes and capture {command, exit_code, last ~5 output lines} VERBATIM —
    never paraphrased, never predicted. No runner → no_runner_detected: true.
+   Coverage: when the project asks for a coverage level, run the coverage ONCE
+   for your own files only (`--collectCoverageFrom=<each file you changed>` and
+   the text reporter), read the uncovered lines from that text table, add the
+   tests that cover them, and run it once more. Never grep lcov or the jest
+   cache, and never probe the test transformer or its internals. A gap that is
+   still open after the second run goes in unmet[] with the file and lines.
 5. Self-check: re-read your diff against every acceptance[] line and every
    constraint. Anything you could not satisfy goes in unmet[] — a non-empty
    unmet[] means status partial (or failed), never done.
@@ -129,12 +140,13 @@ never spawn other agents, never work outside your task slice.
   did, never what you were handed. `none` is a valid, useful answer — it says
   those pages did not help; never claim a read to look thorough. Omit only when
   the slice carried no wiki material.
-- graph_used — REQUIRED when the slice carried `orc graph ctx` cards or you ran
-  `orc graph ctx` yourself: `{targets, generation}` — the card targets you ACTUALLY used (or
-  `none`) and the `generation` number the cards carry, copied from the card's own JSON. A card
+- graph_used — REQUIRED when the slice carried `graph_anchors` or you ran
+  `orc graph ctx` yourself: `{targets, generation}` — the anchors (`path:a-b`) or the
+  card targets you ACTUALLY used (or `none`) and the `generation` number the slice or card
+  carries, copied from its own header or JSON. A card
   is a LOCATOR — read the range it names before you rely on behaviour, and trust a card whose
   header says CHANGED, or one whose header names a `coverage` gap, as a hint only. `none` is a
-  valid answer; never claim a card helped to look thorough. Omit only when the slice carried no cards.
+  valid answer; never claim anchors or a card helped to look thorough. Omit only when the slice carried no anchors and you ran no `ctx`.
 - repro — REQUIRED when the slice carried `repro.required: true`; absent
   otherwise. Either {command, before: {exit_code, tail}, after: {exit_code,
   tail}} quoted VERBATIM from the two runs, or `none` + a one-line reason.