Formulates a targeted defensive security reviewing plan based on the active threat model and historical learnings. Use when starting a security review campaign to map the codebase boundaries and generate a roadmap (workspace/plan.json). Don't use for executing code reviews, writing test scripts, or

Strategist (/mantis plan) System Goal Security Architect. Analyzes code structure, directory metadata, and historical records to map the external boundary and formulate an adaptive review roadmap. Command Definition Command: /mantis plan Description: Formulates a targeted defensive security reviewing plan based on the active threat model and historical learnings. Arguments (optional; supplied by the orchestrator, consumed by Block A): snapshot root / SNAPSHOT ROOT : absolute path to the pinned read only code snapshot (CODE ROOT for all snapshot relative paths). snapshot id / SNAPSHOT ID : the pass snapshot identifier (sentinel + Block B comparisons). state root : absolute path to the workspace/ state dir (plan.json, .mantis state.json, findings/, kb/, archive/). STATE RELATIVE — never prefixed with CODE ROOT. All flags absent MODE OFF/legacy mode (Block A step 1d): behaves exactly as today. Input/Output Contract Reads : workspace/.mantis state.json (to track current loop pass). workspace/kb/THREAT MODEL.md (if exists). workspace/kb/index.md (checks existence to determine Mode A vs B). Mode A: traverses production directories and source files, reads mantis summary.md (if available). Mode B: reads workspace/kb/index.md , workspace/kb/THREAT MODEL.md , workspace/archive/.repro attempts.json (if exists), VCS diffs or file timestamps/hashes. workspace/kb/structural index/manifest.json (to check structural index availability/status). workspace/helpers/query structural index.py (to invoke bounded structural index queries). workspace/.mantis state.json NEW fields: active snapshot.{snapshot id, snapshot pinned, vcs type} , snapshot history (read, written by the meta agent). vcs type is read because Block E branches on it. Plan runs Block E in the LIVE repo root to compute changed files / changed files status (COMPUTED or UNKNOWN) and writes them back to state. Writes : workspace/plan.json . Copies retry eligible finding JSON files from workspace/archive/findings pass K/ or workspace/archive/loopK findings/ (where K is the pass it was archived in) to workspace/findings/ (preserving their original UUID filenames). Preconditions : Codebase must be accessible. Idempotency Guarantee : Overwrites workspace/plan.json directly. In Mode B, copies a finding back verbatim only when Block B is MATCHED and its file is unchanged and present; otherwise it schedules a fresh re discovery investigation. Consults .repro attempts.json under the cache read rule. Instructions Step 0: Locator Resolution (run before everything else) [!NOTE] CURRENT PASS CHECK (defensive; the binding guarantee is on the harness per mantis pipeline adapter Scenario 2): if active snapshot is present AND active snapshot.pass != state.pass number , treat the snapshot as STALE for this pass — STOP "stale active snapshot: pass mismatch" or degrade as HALT ( snapshot pinned effectively false: no authoritative verdicts, Block B NOT MATCHED, reproduce not attempted ). This catches a custom harness that preserved active snapshot across the Stage 15 pass increment without re pinning. The reference meta agent re pins every pass, so this check never fires there. Block B itself cannot detect this (it is snapshot id only, not pass aware). Skill specific notes for the strategist: Plan is a CODE READING stage in Mode A (it crawls production directories); the findings only skip does NOT apply. Mode A crawling and every target files path are SNAPSHOT RELATIVE: crawl and resolve them under CODE ROOT. workspace/kb/ , workspace/plan.json , workspace/.mantis state.json , workspace/archive/ , and workspace/findings/ are STATE RELATIVE: read/write them under state root, NEVER under CODE ROOT. Never write, compile, or generate under CODE ROOT (Block A step 4). The plan script writes ONLY workspace/plan.json (state relative). The VCS diff in Block E runs in the LIVE repo root per Block A step 5, NOT CODE ROOT. Analyze the repository structure and create a detailed defensive security review plan that avoids duplication of prior efforts while digging deep into complex inter procedural paths and un scanned code boundaries. Target Agnosticism Directive: The target you are evaluating may be raw source code, a compiled binary, a firmware blob, or a live staging/dev endpoint. Ground your planning in whatever format the target is currently in. You are authorized and encouraged to use whatever suitable tools are at your disposal (e.g., standard Unix tools, unblob , radare2 , angr , objdump , Ghidra , qemu , unicorn ) to explore the artifact structure. If source code is not available, do not attempt to force a source code workflow (e.g. searching for .c or .py files); adapt and 'do what works' for the artifact at hand. Execute the planning stage as follows: 1. Check for Threat Model Context: Check the knowledge base directory for a workspace/kb/THREAT MODEL.md file. If it exists, read the file it completely to understand the program's official security boundaries, threat actors, assets, high risk interfaces, and trusted inputs. 2. Determine Mode & Retrieve Learnings: Check if the knowledge base index workspace/kb/index.md exists. MODE A: First Pass Exhaustive Mode (No workspace/kb/index.md found): If this is the first run, guarantee complete coverage of the codebase. To avoid hitting output token limits on large repositories, do not generate the workspace/plan.json manually in your text response. Instead, execute a shell command to run a short script in your preferred language that: 1. Uses find or os.walk to crawl all production directories. If a mantis summary.md file exists in a directory, use its contents to understand the directory structure instead of reading every individual source file. Otherwise, crawl all production source code files (e.g., .c , .cpp , .py , .js , .go , .rs , .java ). 2. Ignores test folders, build artifacts, and vendor dependencies (e.g., node modules , .git , tests/ ). 3. Programmatically formats the list into the workspace/plan.json schema and writes it directly to disk. Because this is an automated script, instruct it to use a generic, overarching baseline question for the "question" field (e.g., "Conduct a baseline audit for memory safety and logic flaws"), reserving highly contextual custom questions for Mode B. MODE B: Strategic Learning Mode ( workspace/kb/index.md exists): Read workspace/kb/index.md and workspace/kb/THREAT MODEL.md to review the compounded historical knowledge of the codebase, including trust boundaries, vulnerability classes, and architectural components. Adapt your focus to design new, targeted deep dives and regression reviews for components and files that have histories of vulnerabilities. You may generate the workspace/plan.json manually using your file writing tools for this mode, as the scope will be much narrower. Targeted Re Evaluation & Retries : Review the KB index, entity files, and the reproduction attempt cache file ( workspace/archive/.repro attempts.json if it exists). You must identify findings that need re evaluation or retries: Also read the snapshot context from workspace/.mantis state.json : active snapshot.{snapshot id, snapshot pinned} and snapshot history (both written by the meta agent). Then COMPUTE changed files / changed files status for THIS pass by running Block E below in the LIVE repository root (per Block A step 5 — VCS metadata carve out; the pinned snapshot root strips .git/.hg/.repo, so the diff MUST run against the live tree). Write the computed changed files (array of repo relative paths) and changed files status ( COMPUTED or UNKNOWN ) back to workspace/.mantis state.json , then use them for the rest of the stage. Also write changed files pass = the current pass number from state, so consumers can detect a stale (prior pass) diff. Use the following to know which files changed since the previous pass: CHANGED SINCE PREVIOUS: run in the LIVE repository root (NOT SNAPSHOT ROOT). CUR = current commit/revision; PREV = snapshot history entry BEFORE this pass. If PREV missing OR vcs type in {none,unknown} OR the SNAPSHOT ID for prev or cur is a content:/live:/+content hash fallback OR the diff command errors changed files status = UNKNOWN. Treat EVERY file as CHANGED. NEVER treat as unchanged. NEVER drop. (Note: snapshot pinned false alone is NOT a trigger for UNKNOWN — in HALT mode, active snapshot is present and snapshot history has a PREV entry, so the diff can still run. In MODE OFF — no active snapshot — there is no PREV entry, so PREV is missing and the diff degrades to UNKNOWN, but this does NOT force a full Mode A crawl; see the Mode A trigger below.) Else: git : git diff name status M C diff filter=RAMDCT PREV CUR (the M flag detects renames; C detects copies; name status outputs R<score \told path\tnew path for renames so both old and new paths are visible; diff filter=RAMDCT includes Renamed, Added, Modified, Deleted, Copied, and Type changed files) hg : hg status C rev PREV:CUR ( C / copies shows the source path on a following line for renames/copies; hg codes: A=added, R=removed, M=modified) multi vcs : repo forall c 'git diff name status M C diff filter=RAMDCT PREV CUR' (any error UNKNOWN) A finding's file is CHANGED if any of its code paths (path part) is in the set, OR if its path was renamed to or renamed from (parse R<score \told\tnew lines: both old and new paths are in the changed set). If a finding's primary file appears as a rename source (old path), treat the NEW path as changed too — the bug likely moved with the file. Also apply this cache read rule wherever you inspect workspace/archive/.repro attempts.json . FIRST pick the cache KEY exactly the way mantis reproduce writes it: if the finding has a signature field, the key is that signature ; otherwise the key is stable key = normalized title + "@" + primary file path (title lowercased with all non alphanumerics removed; primary file path = first code paths entry with any trailing :line stripped). THEN read the value V under that key: if V is an integer then count=V and last snapshot=UNKNOWN; if V is an object then count=V.count and last snapshot=V.last snapshot (default UNKNOWN). If no entry is found under the chosen key, also try the OTHER key form before concluding count=0, so a signature keyed writer and a stable key reader never miss each other and wrongly reset the attempt budget. (The cache mixes both value forms AND both key styles during migration.) 1. Schedule for Research: For findings in the archive marked "NEEDS RESEARCH" , schedule a targeted investigation in workspace/plan.json (to gather missing context and resolve them to "VALID" or "FALSE POSITIVE" ). 2. Copy for Retry (snapshot gated) or Re discover: For each archived finding that would otherwise be retry eligible (repro not attempted, or failed to reproduce with fewer than 2 attempts per the cache read rule abo

mantis-plan