feat(agents-canon): AGENTS.md canon everywhere — bootstrap v2.0.0 writes AGENTS.md + CLAUDE.md pointer; 15 skills retarget triggers/rule refs from CLAUDE.md to AGENTS.md (semver bumps); dist rebuilt

skills/using-interns/README.md

@@ -8,7 +8,7 @@ Full design: `.wiki/concepts/interns-design.md` (in this repo) — Layer 1 / 2 /
 
 ## When it triggers
 
-- CLAUDE.md contains `delegate to interns when allowed` (added by `project-bootstrap` 1.6.0+).
+- AGENTS.md contains `delegate to interns when allowed` (added by `project-bootstrap` 2.0.0+).
 - User says: "use interns", "delegate to an intern", "разреши интернов", "allow interns", "go ahead with interns".
 - Claude is about to read 3+ files, or one file > 400 lines, just to build context.
 - Claude is about to update `.wiki/log.md` or write a session summary from a long transcript.

skills/using-interns/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: using-interns
 author: ours
-version: 0.3.1
+version: 0.3.2
 description: >
   Use when delegating predictable bulk reads or summarization to cheap intern LLMs via the l
   ocal `interns` MCP server (`mcp__interns__bulk_text_read`, `mcp__interns__transcript_disti
   ll`, etc.) so the main agent saves quota. Activated by `delegate to interns when allowed` 
-  in CLAUDE.md or explicit phrases: «разреши интернов», "use interns", "allow interns". Also
+  in AGENTS.md or explicit phrases: «разреши интернов», "use interns", "allow interns". Also
    activates proactively when about to read 3+ files for context, a single file >400 lines, 
   or distill a long transcript — surface the offer «знаю, что есть интерны — заюзать?» first
   . Per-session grant mirrors project-discipline Rule 4: ask-mode default, always-ask for `.
@@ -27,7 +27,7 @@ The catalog:
 | `mcp__interns__bulk_text_read` | Reads N files end-to-end and answers a focused question with file:line citations. | Claude was about to read 3+ files or one file > 400 lines just to extract context. |
 | `mcp__interns__transcript_distill` | Compresses a session transcript / log into a structured action list (decisions / open questions / next steps). | Before updating `.wiki/log.md` or producing a session summary. |
 | `mcp__interns__repo_read` | Packs a directory/repo via `repomix` and answers a focused question about the codebase. | Whole-repo or whole-directory questions — architecture, "where is X used", "what does module Y do". See Routing hints for `repo_read` vs `bulk_text_read`. |
-| `mcp__interns__grep_audit` | Deterministic grep matrix over N paths × M patterns. **No LLM call, no endpoint cost.** Returns ✅/❌/⚠️ table or JSON. | Contains/not-contains audits — checking a set of CLAUDE.md / SKILL.md / frontmatter files for canonical strings. See Routing hints for `grep_audit` vs `bulk_text_read`. |
+| `mcp__interns__grep_audit` | Deterministic grep matrix over N paths × M patterns. **No LLM call, no endpoint cost.** Returns ✅/❌/⚠️ table or JSON. | Contains/not-contains audits — checking a set of AGENTS.md / CLAUDE.md / SKILL.md / frontmatter files for canonical strings. See Routing hints for `grep_audit` vs `bulk_text_read`. |
 
 LLM-backed interns currently run on Ollama Cloud (`deepseek-v4-flash`, ~$0.002 / call). `grep_audit` is the catalog's first LLM-free intern — zero cost, zero hallucination boundary. Adding a new intern is a config-only change — see `.wiki/concepts/interns-design.md` § "Как добавить нового интерна".
 
@@ -142,7 +142,7 @@ Any call with estimated cost > $0.10 (per the `tokens × price_per_M` config in
 | Don't delegate editing or debugging a specific file to `repo_read` | Read the file yourself. `repo_read` is for comprehension, not modification. |
 | Updating `.wiki/log.md` or session-summary doc | `transcript_distill` |
 | Compressing a long brainstorm transcript before quoting in a design doc | `transcript_distill` |
-| Audit N paths × M patterns (contains/not-contains matrix — checking CLAUDE.md / SKILL.md / frontmatter for canonical strings) | `grep_audit` — deterministic, no LLM call, zero cost, zero hallucination boundary |
+| Audit N paths × M patterns (contains/not-contains matrix — checking AGENTS.md / CLAUDE.md / SKILL.md / frontmatter for canonical strings) | `grep_audit` — deterministic, no LLM call, zero cost, zero hallucination boundary |
 | `bulk_text_read` vs `grep_audit` | `bulk_text_read` is Q&A with an LLM over files; `grep_audit` is deterministic contains/not-contains. Semantic match (paraphrase, intent) → `bulk_text_read` with a question, not `grep_audit`. |
 | Always-ask paths apply uniformly to `grep_audit` | The server still opens the file even without an LLM call — no special "safe intern" carve-out. Same `.env` / secrets / keys / SSH gate as the LLM-backed interns. |
 | (Future interns in `config.yaml`) | per the description in the catalog |