mapify-cli 3.10.0__tar.gz → 3.12.0__tar.gz

{mapify_cli-3.10.0 → mapify_cli-3.12.0}/.claude/hooks/README.md

@@ -86,16 +86,33 @@ documented per event in the official Claude Code docs.
 
 ## Hook inventory
 
-| Hook | Event | Blocking? | Purpose |
-|------|-------|-----------|---------|
-| `safety-guardrails.py` | `PreToolUse` (Edit/Write/Read/MultiEdit/Bash) | Yes (JSON deny) | Block sensitive files, dangerous commands |
-| `workflow-gate.py` | `PreToolUse` (Edit/Write/MultiEdit) | Yes (JSON deny) | Enforce Actor+Monitor workflow before edits |
-| `workflow-context-injector.py` | `PreToolUse` (Edit/Write/Bash) | No | Inject MAP workflow reminder |
-| `ralph-iteration-logger.py` | `PostToolUse` | No | Log iterations, detect file thrashing |
-| `ralph-context-pruner.py` | `PreCompact` | No | Save restore point, prune logs |
-| `pre-compact-save-transcript.py` | `PreCompact` | No | Save full conversation transcript |
-| `post-compact-context.py` | `SessionStart` (compact) | No | Inject restore-point context |
-| `end-of-turn.sh` | `Stop` | No | Auto-fix lint/format silently |
-| `detect-clarification-triggers.py` | `UserPromptSubmit` | No | Detect "ask if unclear" + async/durability language |
-
-Last reviewed: 2026-04-28.
+All 15 hooks (14 `.py` + `end-of-turn.sh`) are classified against the
+`MAP_INVOKED_BY` recursion-guard contract. **REQUIRE_GUARD** hooks early-exit
+when MAP spawns a nested subprocess; **FORBID_GUARD** hooks must always fire
+and may not carry the guard. Full contract and per-hook rationale:
+[`../references/hook-patterns.md`](../references/hook-patterns.md). The
+classification is enforced by `scripts/lint-hooks.py` (in `make lint` /
+`make check`).
+
+| Hook | Event | Blocking? | Class | Purpose |
+|------|-------|-----------|-------|---------|
+| `safety-guardrails.py` | `PreToolUse` (Edit/Write/Read/MultiEdit/Bash) | Yes (JSON deny) | FORBID_GUARD | Block sensitive files, dangerous commands |
+| `workflow-gate.py` | `PreToolUse` (Edit/Write/MultiEdit) | Yes (JSON deny) | FORBID_GUARD | Enforce Actor+Monitor workflow before edits |
+| `post-compact-context.py` | `SessionStart` (compact) | No | FORBID_GUARD | Inject restore-point context (re-prime after compaction) |
+| `context-meter.py` | `UserPromptSubmit` | No | REQUIRE_GUARD | Nudge `/compact <focus>` when the token threshold is crossed |
+| `map-token-meter.py` | `SubagentStop` + `Stop` | No | REQUIRE_GUARD | Attribute per-turn token usage to the active MAP subtask |
+| `workflow-context-injector.py` | `PreToolUse` (Edit/Write/Bash) | No | REQUIRE_GUARD | Inject MAP workflow reminder |
+| `ralph-iteration-logger.py` | `PostToolUse` | No | REQUIRE_GUARD | Log iterations, detect file thrashing |
+| `ralph-context-pruner.py` | `PreCompact` | No | REQUIRE_GUARD | Save restore point, prune logs |
+| `pre-compact-save-transcript.py` | `PreCompact` | No | REQUIRE_GUARD | Save full conversation transcript |
+| `detect-clarification-triggers.py` | `UserPromptSubmit` | No | REQUIRE_GUARD | Detect "ask if unclear" + async/durability language |
+| `end-of-turn.sh` | `Stop` | No | REQUIRE_GUARD | Auto-fix lint/format silently |
+| `map-memory-capture.py` | `Stop` | No | REQUIRE_GUARD | Append per-turn scratch WAL record (cross-session memory) |
+| `map-memory-endmark.py` | `SessionEnd` | No | REQUIRE_GUARD | Best-effort 'ended' marker for the session WAL |
+| `map-memory-finalize.py` | `SessionStart` | No | REQUIRE_GUARD | Finalize prior dirty session scratches into digests (claude -p) |
+| `map-memory-recall.py` | `SessionStart` + `UserPromptSubmit` | No | REQUIRE_GUARD | Inject ranked recalled session memory (additionalContext) |
+
+> The Codex twin `.codex/hooks/workflow-gate.py` is FORBID_GUARD like its
+> Claude counterpart; this inventory covers `.claude/hooks/` only.
+
+Last reviewed: 2026-05-29.

{mapify_cli-3.10.0/src/mapify_cli/templates → mapify_cli-3.12.0/.claude}/skills/README.md

@@ -63,8 +63,8 @@ The development copy under `.claude/skills/` must stay byte-for-byte synced with
 Use:
 
 ```bash
-make sync-templates
-pytest tests/test_skills.py tests/test_template_sync.py -v
+make render-templates
+pytest tests/test_skills.py tests/test_template_render.py -v
 ```
 
 ## Troubleshooting

{mapify_cli-3.10.0 → mapify_cli-3.12.0}/.gitignore

@@ -49,6 +49,15 @@ coverage.json
 !.map/static-analysis/
 !.map/scripts/
 .map/scripts/.map/
+.map/personal/
+# ^ Personal/local learned-rules layer — user-local, never committed or shipped
+#   (redundant over .map/* above; kept explicit for intent + defense in depth)
+
+# Phase E cross-session memory: scratch WAL is transient (never commit)
+.map/*/sessions/scratch/
+# Digests (.map/*/sessions/*.md) are committed by default. To keep them
+# local, set MAP_MEMORY_COMMIT_DIGESTS=0 and uncomment the next line:
+# .map/*/sessions/
 
 # Temporary verification files
 mapify_cli_verification_*.json
@@ -71,8 +80,18 @@ docs/claude-code-prompt-improver
 .mcp.json
 .chunkhound/
 docs/planning-with-files.txt
+docs/map_framework_tech_directors.pptx
+docs/map-demo-real-case-plan.md
+uv.lock
 docs/research/
 docs/superpowers/
 
 # Hypothesis test cache
 .hypothesis/
+
+# Presentation materials (AIADOPTION-765 demo + tech-directors deck) — local only, never committed
+ai-yc-presetation/
+docs/map-framework-tech-directors-stackland1144-draft.md
+docs/map_framework_tech_directors_stackland1144_map_plan_draft.pptx
+# map:sofa — SOFA credential dir (opt-in); never commit. See docs/USAGE.md
+.sofa/

{mapify_cli-3.10.0 → mapify_cli-3.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mapify-cli
-Version: 3.10.0
+Version: 3.12.0
 Summary: MAP Framework installer - Modular Agentic Planner for Claude Code
 Project-URL: Homepage, https://github.com/azalio/map-framework
 Project-URL: Repository, https://github.com/azalio/map-framework.git
@@ -8,6 +8,7 @@ Project-URL: Issues, https://github.com/azalio/map-framework/issues
 Author: MAP Framework Contributors
 Requires-Python: >=3.11
 Requires-Dist: httpx>=0.25.0
+Requires-Dist: jinja2<4,>=3.1
 Requires-Dist: platformdirs>=4.0.0
 Requires-Dist: questionary>=2.0.0
 Requires-Dist: readchar>=4.0.0
@@ -18,8 +19,11 @@ Requires-Dist: black>=23.0.0; extra == 'dev'
 Requires-Dist: hypothesis>=6.0.0; extra == 'dev'
 Requires-Dist: jsonschema>=4.0.0; extra == 'dev'
 Requires-Dist: mypy>=1.0.0; extra == 'dev'
+Requires-Dist: pyright>=1.1.400; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.26.0; extra == 'dev'
 Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
 Requires-Dist: pytest-mock>=3.10.0; extra == 'dev'
+Requires-Dist: pytest-timeout>=2.1.0; extra == 'dev'
 Requires-Dist: pytest>=7.0.0; extra == 'dev'
 Requires-Dist: pyyaml>=6.0.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
@@ -29,8 +33,10 @@ Requires-Dist: truststore>=0.9.0; extra == 'ssl'
 Provides-Extra: test
 Requires-Dist: hypothesis>=6.0.0; extra == 'test'
 Requires-Dist: jsonschema>=4.0.0; extra == 'test'
+Requires-Dist: pytest-asyncio>=0.26.0; extra == 'test'
 Requires-Dist: pytest-cov>=4.0.0; extra == 'test'
 Requires-Dist: pytest-mock>=3.10.0; extra == 'test'
+Requires-Dist: pytest-timeout>=2.1.0; extra == 'test'
 Requires-Dist: pytest>=7.0.0; extra == 'test'
 Requires-Dist: pyyaml>=6.0.0; extra == 'test'
 Description-Content-Type: text/markdown
@@ -115,15 +121,34 @@ Then enable the Codex hook manually: run `/hooks`, select `PreToolUse`, press `t
 
 If your Codex version does not support the `hooks` feature key yet, either start it with `codex --enable codex_hooks` or upgrade Codex first. Upgrading is recommended.
 
-Pick a context-compression policy if you want non-default behaviour
-(`auto` is the default; see [docs/USAGE.md#context-budget-policy](docs/USAGE.md)):
+Pick a context-compression policy if you want the `/compact` nudge
+(default is `never` — the nudge is opt-in; see
+[docs/USAGE.md#context-budget-policy](docs/USAGE.md)):
 
 ```bash
-mapify init . --compression never                 # quality > cost
-mapify init . --compression aggressive            # cost > quality
-mapify init . --compression-threshold 250000      # Opus 1M project
+mapify init . --compression never                 # default — no nudge
+mapify init . --compression auto                  # nudge at threshold
+mapify init . --compression aggressive            # nudge at 0.4 x threshold
+mapify init . --compression-threshold 250000      # Opus 1M / 50+ subtask plans
 ```
 
+Context-block / review-prompt truncation was removed: Actor and reviewer
+prompts always carry the full bundled context. If the conversation grows
+beyond your model's window, opt into `/compact` via `--compression auto` or
+trigger it manually.
+
+Optionally opt into **Stack Overflow for Agents (SOFA)** read-only prior-art
+search — **off by default**, no network or credentials unless you enable it:
+
+```bash
+mapify init . --sofa            # opt-in: enable the map-so-search skill
+```
+
+This writes `sofa.enabled: true` to `.map/config.yaml` and adds `.sofa/` to your
+`.gitignore`. Without the flag, no SOFA code path runs. See the
+[SOFA usage guide](docs/USAGE.md#stack-overflow-for-agents-sofa) for onboarding
+and the untrusted-content boundary.
+
 **3. Use the golden path for serious work**
 
 When a task has unclear behavior, multiple files, or real review risk, run the full loop:
@@ -156,12 +181,19 @@ MAP review is useful, but it is not a replacement for engineering judgment. Seri
 
 - **Daily-driver speed** - optimized for repeated use, not occasional demo workflows.
 - **Low overhead** - structured enough to prevent chaos, lightweight enough to keep token and time cost under control.
+- **Compact high-traffic playbooks** - `/map-plan`, `/map-efficient`, `/map-check`, and `/map-review` keep their active `SKILL.md` bodies focused on the next workflow action, with detailed examples and troubleshooting in bundled supporting files that load only when needed.
 - **Calibrated workflow effort** - each shipped slash skill declares a `thinking_policy` and `parallel_tool_policy`, so lightweight commands stay direct while planning, review, and release workflows reserve deeper reasoning and parallel fan-out for the stages that benefit from it. Non-release prompts use targeted guardrails instead of blanket all-caps prohibition blocks, reducing over-triggered agents and tool calls while keeping true hard stops explicit.
+- **Mutation boundary constraints** - write-capable Claude and Codex provider surfaces tell agents not to edit unrelated files, add or upgrade dependencies, or refactor neighboring code unless the current task/subtask explicitly requires it. If broader scope is necessary, agents should report it as a blocker or tradeoff instead of silently expanding the diff.
+- **Context-first prompt envelopes** - high-context `/map-plan`, `/map-efficient`, `/map-debug`, and `/map-review` agent prompts wrap branch artifacts in XML-style `<documents>`, then state the `<task>` and `<expected_output>`, so specs, review bundles, diffs, logs, and schemas stay visually and machine-semantically separated.
+- **Skill IR audit** - release checks can lower shipped Claude and Codex `SKILL.md` files into a typed `SkillIR`, verify content hashes, catch unsupported frontmatter, reject missing supporting-file links, and block injection-like instructions before `mapify init` copies provider surfaces into user repos.
 - **Reviewable diffs** - planning and task contracts keep changes small enough to inspect.
 - **Contract-sized subtasks** - `/map-plan` and `/map-efficient` require per-subtask `expected_diff_size`, `concern_type`, `one_logical_step`, `hard_constraints`, `soft_constraints`, and `coverage_map` metadata, then validate `blueprint.json` before implementation so oversized, mixed-concern, untraceable, or hard-constraint-dropping plans fail early instead of surprising reviewers later. Soft constraints can be consciously traded off only with explicit rationale.
 - **Useful quality gates** - `/map-check` and `/map-review` validate against the plan instead of just asking whether code "looks fine".
-- **Review bundle** - `/map-review` auto-generates `.map/<branch>/review-bundle.json` and `.map/<branch>/review-bundle.md` before launching reviewer agents, bundling spec, plan, tests, verification, latest code review, `coverage_map` acceptance-tag evidence, and prior-stage consumption status into a single durable input contract. Reviewers read the bundle first; raw diff is secondary. Use `/map-review --detached` to open an isolated read-only git worktree at `.map/<branch>/detached-review/` for clean-room inspection without touching the source branch. Bundle generation records the `review` stage in `.map/<branch>/artifact_manifest.json`; `python3 .map/scripts/map_step_runner.py validate_prior_stage_consumption review` can fail missing spec/blueprint/test/diff inputs before review. Section-order flags reduce anchoring bias: `--reverse-sections` (invert order), `--shuffle-sections [--seed N]` (seeded random order), `--compare-orderings` (run default + reverse, aggregate via strict-wins, surface drift).
+- **Review bundle** - `/map-review` auto-generates `.map/<branch>/review-bundle.json` and `.map/<branch>/review-bundle.md` before launching reviewer agents, bundling spec, plan, tests, verification, latest code review, `coverage_map` acceptance-tag evidence, and prior-stage consumption status into a single durable input contract. Reviewers read the bundle first; raw diff is secondary and is clipped first when `build_review_prompts` has to keep each reviewer prompt under `MAP_REVIEW_PROMPT_BUDGET_TOKENS`. Use `/map-review --detached` to open an isolated read-only git worktree at `.map/<branch>/detached-review/` for clean-room inspection without touching the source branch. Bundle generation records the `review` stage in `.map/<branch>/artifact_manifest.json`; `python3 .map/scripts/map_step_runner.py validate_prior_stage_consumption review` can fail missing spec/blueprint/test/diff inputs before review. Section-order flags reduce anchoring bias: `--reverse-sections` (invert order), `--shuffle-sections [--seed N]` (seeded random order), `--compare-orderings` (run default + reverse, aggregate via strict-wins, surface drift).
+- **Token budget report** - Actor context and review fan-out prompt builders append active-path budget decisions to `.map/<branch>/token_budget.json`, including before/after estimated tokens, clipped sections, source artifact references, and the budget environment variable. This is the operator breadcrumb for diagnosing missing context: inspect the report, then either raise `MAP_CONTEXT_BLOCK_BUDGET_TOKENS` / `MAP_REVIEW_PROMPT_BUDGET_TOKENS` or split the workflow before rerunning.
+- **Clean retry quarantine** - after repeated Monitor rejection, write-capable workflows switch the next Actor attempt into clean-retry mode and use `.map/<branch>/retry_quarantine.json` instead of raw failed-session context. The artifact preserves constraints, required evidence, and do-not-repeat feedback so retries can change approach without dropping the contract.
 - **Run health report** - `/map-efficient`, `/map-debug`, `/map-check`, and `/map-review` write `.map/<branch>/run_health_report.json` during closeout via `.map/scripts/map_step_runner.py write_run_health_report`. The report is a machine-readable snapshot of terminal status, step progress, retry counters, artifact presence, and latest hook-injection status, including explicit skipped reasons for malformed hook input or insignificant Bash commands when branch state can be safely updated. CI or operators can fail inconsistent closeouts with `python3 .map/scripts/map_step_runner.py validate_run_health_report`.
+- **Compact recovery surface** - `/map-resume` keeps the active recovery flow in a short `SKILL.md` and moves low-frequency examples, state-file notes, token-budget notes, and troubleshooting into `resume-reference.md`, so users recovering after `/clear` or context exhaustion get the next checkpoint action without loading the whole reference appendix.
 - **Project memory** - `/map-learn` turns hard-won fixes and gotchas into reusable context for the next session.
 
 ## Core Commands
@@ -221,7 +253,9 @@ Learner        -> captures reusable project memory
 
 For Claude Code, MAP slash surfaces live in `.claude/skills/map-*/SKILL.md` files created by `mapify init`. The `.claude/commands/` directory is reserved for user-custom commands and a README that points back to the skill-backed MAP surfaces. The shipped skill catalog classifies skills with `skillClass`: MAP slash workflows are `task` skills, while `map-state` is a `hybrid` skill because it combines planning guidance with hooks/scripts that manage `.map/<branch>/` focus artifacts.
 
-For Codex CLI, `mapify init . --provider codex` creates `.codex/skills/`, `.codex/agents/`, `.codex/config.toml`, hooks, and shared `.map/scripts/`.
+For Codex CLI, `mapify init . --provider codex` creates `.agents/skills/` for repository skills, `.codex/agents/`, `.codex/config.toml`, hooks, and shared `.map/scripts/`.
+
+Maintainers can audit both provider skill trees with `python -m mapify_cli.skill_ir src/mapify_cli/templates/skills src/mapify_cli/templates/codex/skills`. The command exits non-zero if a shipped skill has unsupported frontmatter, unresolved bundled references, or hidden prompt-injection-like text.
 
 MAP is inspired by [MAP cognitive architecture](https://github.com/Shanka123/MAP) (Nature Communications, 2025), which reported a 74% improvement in planning tasks. The CLI turns that idea into a practical software development workflow.
 

{mapify_cli-3.10.0 → mapify_cli-3.12.0}/README.md

@@ -78,15 +78,34 @@ Then enable the Codex hook manually: run `/hooks`, select `PreToolUse`, press `t
 
 If your Codex version does not support the `hooks` feature key yet, either start it with `codex --enable codex_hooks` or upgrade Codex first. Upgrading is recommended.
 
-Pick a context-compression policy if you want non-default behaviour
-(`auto` is the default; see [docs/USAGE.md#context-budget-policy](docs/USAGE.md)):
+Pick a context-compression policy if you want the `/compact` nudge
+(default is `never` — the nudge is opt-in; see
+[docs/USAGE.md#context-budget-policy](docs/USAGE.md)):
 
 ```bash
-mapify init . --compression never                 # quality > cost
-mapify init . --compression aggressive            # cost > quality
-mapify init . --compression-threshold 250000      # Opus 1M project
+mapify init . --compression never                 # default — no nudge
+mapify init . --compression auto                  # nudge at threshold
+mapify init . --compression aggressive            # nudge at 0.4 x threshold
+mapify init . --compression-threshold 250000      # Opus 1M / 50+ subtask plans
 ```
 
+Context-block / review-prompt truncation was removed: Actor and reviewer
+prompts always carry the full bundled context. If the conversation grows
+beyond your model's window, opt into `/compact` via `--compression auto` or
+trigger it manually.
+
+Optionally opt into **Stack Overflow for Agents (SOFA)** read-only prior-art
+search — **off by default**, no network or credentials unless you enable it:
+
+```bash
+mapify init . --sofa            # opt-in: enable the map-so-search skill
+```
+
+This writes `sofa.enabled: true` to `.map/config.yaml` and adds `.sofa/` to your
+`.gitignore`. Without the flag, no SOFA code path runs. See the
+[SOFA usage guide](docs/USAGE.md#stack-overflow-for-agents-sofa) for onboarding
+and the untrusted-content boundary.
+
 **3. Use the golden path for serious work**
 
 When a task has unclear behavior, multiple files, or real review risk, run the full loop:
@@ -119,12 +138,19 @@ MAP review is useful, but it is not a replacement for engineering judgment. Seri
 
 - **Daily-driver speed** - optimized for repeated use, not occasional demo workflows.
 - **Low overhead** - structured enough to prevent chaos, lightweight enough to keep token and time cost under control.
+- **Compact high-traffic playbooks** - `/map-plan`, `/map-efficient`, `/map-check`, and `/map-review` keep their active `SKILL.md` bodies focused on the next workflow action, with detailed examples and troubleshooting in bundled supporting files that load only when needed.
 - **Calibrated workflow effort** - each shipped slash skill declares a `thinking_policy` and `parallel_tool_policy`, so lightweight commands stay direct while planning, review, and release workflows reserve deeper reasoning and parallel fan-out for the stages that benefit from it. Non-release prompts use targeted guardrails instead of blanket all-caps prohibition blocks, reducing over-triggered agents and tool calls while keeping true hard stops explicit.
+- **Mutation boundary constraints** - write-capable Claude and Codex provider surfaces tell agents not to edit unrelated files, add or upgrade dependencies, or refactor neighboring code unless the current task/subtask explicitly requires it. If broader scope is necessary, agents should report it as a blocker or tradeoff instead of silently expanding the diff.
+- **Context-first prompt envelopes** - high-context `/map-plan`, `/map-efficient`, `/map-debug`, and `/map-review` agent prompts wrap branch artifacts in XML-style `<documents>`, then state the `<task>` and `<expected_output>`, so specs, review bundles, diffs, logs, and schemas stay visually and machine-semantically separated.
+- **Skill IR audit** - release checks can lower shipped Claude and Codex `SKILL.md` files into a typed `SkillIR`, verify content hashes, catch unsupported frontmatter, reject missing supporting-file links, and block injection-like instructions before `mapify init` copies provider surfaces into user repos.
 - **Reviewable diffs** - planning and task contracts keep changes small enough to inspect.
 - **Contract-sized subtasks** - `/map-plan` and `/map-efficient` require per-subtask `expected_diff_size`, `concern_type`, `one_logical_step`, `hard_constraints`, `soft_constraints`, and `coverage_map` metadata, then validate `blueprint.json` before implementation so oversized, mixed-concern, untraceable, or hard-constraint-dropping plans fail early instead of surprising reviewers later. Soft constraints can be consciously traded off only with explicit rationale.
 - **Useful quality gates** - `/map-check` and `/map-review` validate against the plan instead of just asking whether code "looks fine".
-- **Review bundle** - `/map-review` auto-generates `.map/<branch>/review-bundle.json` and `.map/<branch>/review-bundle.md` before launching reviewer agents, bundling spec, plan, tests, verification, latest code review, `coverage_map` acceptance-tag evidence, and prior-stage consumption status into a single durable input contract. Reviewers read the bundle first; raw diff is secondary. Use `/map-review --detached` to open an isolated read-only git worktree at `.map/<branch>/detached-review/` for clean-room inspection without touching the source branch. Bundle generation records the `review` stage in `.map/<branch>/artifact_manifest.json`; `python3 .map/scripts/map_step_runner.py validate_prior_stage_consumption review` can fail missing spec/blueprint/test/diff inputs before review. Section-order flags reduce anchoring bias: `--reverse-sections` (invert order), `--shuffle-sections [--seed N]` (seeded random order), `--compare-orderings` (run default + reverse, aggregate via strict-wins, surface drift).
+- **Review bundle** - `/map-review` auto-generates `.map/<branch>/review-bundle.json` and `.map/<branch>/review-bundle.md` before launching reviewer agents, bundling spec, plan, tests, verification, latest code review, `coverage_map` acceptance-tag evidence, and prior-stage consumption status into a single durable input contract. Reviewers read the bundle first; raw diff is secondary and is clipped first when `build_review_prompts` has to keep each reviewer prompt under `MAP_REVIEW_PROMPT_BUDGET_TOKENS`. Use `/map-review --detached` to open an isolated read-only git worktree at `.map/<branch>/detached-review/` for clean-room inspection without touching the source branch. Bundle generation records the `review` stage in `.map/<branch>/artifact_manifest.json`; `python3 .map/scripts/map_step_runner.py validate_prior_stage_consumption review` can fail missing spec/blueprint/test/diff inputs before review. Section-order flags reduce anchoring bias: `--reverse-sections` (invert order), `--shuffle-sections [--seed N]` (seeded random order), `--compare-orderings` (run default + reverse, aggregate via strict-wins, surface drift).
+- **Token budget report** - Actor context and review fan-out prompt builders append active-path budget decisions to `.map/<branch>/token_budget.json`, including before/after estimated tokens, clipped sections, source artifact references, and the budget environment variable. This is the operator breadcrumb for diagnosing missing context: inspect the report, then either raise `MAP_CONTEXT_BLOCK_BUDGET_TOKENS` / `MAP_REVIEW_PROMPT_BUDGET_TOKENS` or split the workflow before rerunning.
+- **Clean retry quarantine** - after repeated Monitor rejection, write-capable workflows switch the next Actor attempt into clean-retry mode and use `.map/<branch>/retry_quarantine.json` instead of raw failed-session context. The artifact preserves constraints, required evidence, and do-not-repeat feedback so retries can change approach without dropping the contract.
 - **Run health report** - `/map-efficient`, `/map-debug`, `/map-check`, and `/map-review` write `.map/<branch>/run_health_report.json` during closeout via `.map/scripts/map_step_runner.py write_run_health_report`. The report is a machine-readable snapshot of terminal status, step progress, retry counters, artifact presence, and latest hook-injection status, including explicit skipped reasons for malformed hook input or insignificant Bash commands when branch state can be safely updated. CI or operators can fail inconsistent closeouts with `python3 .map/scripts/map_step_runner.py validate_run_health_report`.
+- **Compact recovery surface** - `/map-resume` keeps the active recovery flow in a short `SKILL.md` and moves low-frequency examples, state-file notes, token-budget notes, and troubleshooting into `resume-reference.md`, so users recovering after `/clear` or context exhaustion get the next checkpoint action without loading the whole reference appendix.
 - **Project memory** - `/map-learn` turns hard-won fixes and gotchas into reusable context for the next session.
 
 ## Core Commands
@@ -184,7 +210,9 @@ Learner        -> captures reusable project memory
 
 For Claude Code, MAP slash surfaces live in `.claude/skills/map-*/SKILL.md` files created by `mapify init`. The `.claude/commands/` directory is reserved for user-custom commands and a README that points back to the skill-backed MAP surfaces. The shipped skill catalog classifies skills with `skillClass`: MAP slash workflows are `task` skills, while `map-state` is a `hybrid` skill because it combines planning guidance with hooks/scripts that manage `.map/<branch>/` focus artifacts.
 
-For Codex CLI, `mapify init . --provider codex` creates `.codex/skills/`, `.codex/agents/`, `.codex/config.toml`, hooks, and shared `.map/scripts/`.
+For Codex CLI, `mapify init . --provider codex` creates `.agents/skills/` for repository skills, `.codex/agents/`, `.codex/config.toml`, hooks, and shared `.map/scripts/`.
+
+Maintainers can audit both provider skill trees with `python -m mapify_cli.skill_ir src/mapify_cli/templates/skills src/mapify_cli/templates/codex/skills`. The command exits non-zero if a shipped skill has unsupported frontmatter, unresolved bundled references, or hidden prompt-injection-like text.
 
 MAP is inspired by [MAP cognitive architecture](https://github.com/Shanka123/MAP) (Nature Communications, 2025), which reported a 74% improvement in planning tasks. The CLI turns that idea into a practical software development workflow.
 

mapify_cli-3.12.0/pyproject.toml

@@ -0,0 +1,124 @@
+[project]
+name = "mapify-cli"
+version = "3.12.0"
+description = "MAP Framework installer - Modular Agentic Planner for Claude Code"
+authors = [{ name = "MAP Framework Contributors" }]
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "typer>=0.9.0",
+    "rich>=13.0.0",
+    "httpx>=0.25.0",
+    "jinja2>=3.1,<4",
+    "platformdirs>=4.0.0",
+    "readchar>=4.0.0",
+    "questionary>=2.0.0"
+]
+
+[project.optional-dependencies]
+ssl = ["truststore>=0.9.0"]
+test = [
+    "pytest>=7.0.0",
+    "pytest-asyncio>=0.26.0",
+    "pytest-cov>=4.0.0",
+    "pytest-mock>=3.10.0",
+    "pytest-timeout>=2.1.0",
+    "pyyaml>=6.0.0",
+    "hypothesis>=6.0.0",
+    "jsonschema>=4.0.0",
+]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-asyncio>=0.26.0",
+    "pytest-cov>=4.0.0",
+    "pytest-mock>=3.10.0",
+    "pytest-timeout>=2.1.0",
+    "pyyaml>=6.0.0",
+    "hypothesis>=6.0.0",
+    "jsonschema>=4.0.0",
+    "black>=23.0.0",
+    "ruff>=0.1.0",
+    "mypy>=1.0.0",
+    "pyright>=1.1.400",
+    "truststore>=0.9.0",
+]
+
+[project.scripts]
+mapify = "mapify_cli:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build]
+include = [
+    "src/**/*.py",
+    "src/mapify_cli/templates/**/*",
+    "src/mapify_cli/templates_src/**/*.jinja",
+    "README.md",
+]
+exclude = [
+    "**/__pycache__/**",
+    "**/*.pyc",
+    "**/*.pyo",
+    "**/.DS_Store",
+]
+artifacts = [
+    "src/mapify_cli/templates/**/*",
+    "src/mapify_cli/templates_src/**/*.jinja",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/mapify_cli"]
+# NOTE: do NOT force-include src/mapify_cli/templates_src here. It already lands
+# in the wheel under mapify_cli/templates_src via `packages` + the global
+# [tool.hatch.build] include/artifacts patterns for templates_src/**/*.jinja.
+# A force-include duplicates every .jinja at the same archive path, which newer
+# hatchling rejects with "A second file is being added ... at the same path".
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "src/**/*.py",
+    "src/mapify_cli/templates/**/*",
+    "src/mapify_cli/templates_src/**/*.jinja",
+    "tests/**/*",
+    "README.md",
+    "LICENSE",
+    "pyproject.toml",
+]
+
+[tool.mypy]
+ignore_missing_imports = false
+exclude = [
+    "src/mapify_cli/templates/map/scripts/",
+    "tests/skills_eval/fixtures/whole_skill/",
+]
+
+# Intentionally-broken seeded mini-repos used as whole-skill eval fixtures
+# (e.g. a test importing a deliberately-absent module). They are seeded into a
+# temp cwd at run time, never imported by the package — exclude from static
+# analysis and the language server.
+[tool.pyright]
+# Pin import resolution to the project venv so `make lint` is deterministic
+# regardless of which `pyright` is on PATH (e.g. a global Homebrew/node build
+# that otherwise ignores .venv and spuriously reports unresolved imports).
+venvPath = "."
+venv = ".venv"
+exclude = [
+    "**/node_modules",
+    "**/__pycache__",
+    "**/.*",
+    "tests/skills_eval/fixtures/whole_skill",
+]
+
+[tool.ruff]
+extend-exclude = ["tests/skills_eval/fixtures/whole_skill"]
+
+[[tool.mypy.overrides]]
+module = "yaml"
+ignore_missing_imports = true
+
+[project.urls]
+Homepage = "https://github.com/azalio/map-framework"
+Repository = "https://github.com/azalio/map-framework.git"
+Issues = "https://github.com/azalio/map-framework/issues"