Tactical Playbook

The reconciled tactical execution behind the AI-Native SDLC — the exact skills, hooks, agents, and file names behind each stage, checked against Anthropic's published playbook.

The AI-Native SDLC is the what and why. This page is the how.

How our stages map to Anthropic's 6

Anthropic's playbook runs six stages: Plan → Design → Build → Test → Deploy → Maintain. Sparq splits the first stage into two gates, sold together as one commercial unit — the Evidence Sprint. This is the actual differentiator.

Sparq stageAnthropic stageWhat Sparq adds
0 · Intent FramingPlanStructured workshop (2–4 hrs) + strict inline assumption-tagging before intent.md exists
1 · Evidence GatePlanRequired external-signal checkpoint (Promote/Iterate/Pivot/Stop) + tracker sync and merge on close
2 · DesignDesign1:1
3 · BuildBuild1:1
4 · TestTest1:1
5 · DeployDeploy1:1
6 · MaintainMaintain1:1, plus product-analytics bands widened beyond Anthropic's infra-only example

Commercially: Stages 0–1 together are the Evidence Sprint — the thing that used to be pitched as discovery, now scoped to roughly 2 weeks because the output is evidence and a costed Build decision, not a stack of workshop artifacts. Everything from Design onward tracks Anthropic's canonical mechanics closely.

Stage 0 · Intent Framing — Tactical

First half of the Evidence Sprint.

Practice

A 2–4 hour structured workshop. 10 min silent assumption dump sorted into Value / Usability / Feasibility / Viability / Operational → failure premortem → architecture exposure with engineering. No untagged claims survive the file.

Tooling

Meeting-transcription MCP (Whisper/Fathom/Recall.ai) for live capture, plus Miro/Mural/Slack MCP for stickies and threads.

intent-elicitor skill

Interactive elicitation — asks probing questions, rephrases claims as testable assertions.

assumption-extractor skill

Parses the transcript in real time and auto-tags into the 5 risk categories.

premortem-adversary subagent

Red-teams the room on technical constraints and unstated dependencies.

assumption-linter hook

Pre-commit. Rejects the commit if any claim lacks an [ASSUMPTION: Category] tag.

Artifact: raw intent.md, 100% tagged. Facilitator validates tagging before it moves.

Stage 1 · Evidence Gate — Tactical

Second half of the Evidence Sprint — the execution part of discovery.

Practice

Pull the highest-risk Value/Usability assumption. Frame a minimal external-facing slice. Attach it to a real client touchpoint — synthetic-only validation is disallowed without a logged exception. Record signal. Product + Delivery decide: Promote / Iterate / Pivot / Stop. On a Promote, close by merging cleared intent.md into /intent/, mapping scope blocks into the enterprise tracker, and defining hard boundary markers.

Repo home

Evidence Work skills and the resulting evidence-of-signal live in a per-project repo. That's also where the ESOA lives — transitioning from a solutions-side version into the delivery-side version rather than being recreated.

Vision Prototype

Distinct from the narrow Evidence Slice. Where an Evidence Slice tests one assumption, a Vision Prototype is a holistic build — full breadth, selective depth — meant to show the client the future-state value, not validate a single risk. Optional per engagement, but when built, it sits alongside the Promote decision and the costed Build proposal.

Tooling

Conversation Intelligence MCP (Gong/Zoom/Teams/Chorus) for signal capture; Enterprise Tracker MCP (Jira/Azure DevOps/ServiceNow) and a non-interactive Claude CI runner for the close.

evidence-synthesizer skill

Maps quotes to tagged assumptions, evaluates signal strength, and caps internal-only feedback at Directional confidence so it can't be mistaken for a real-occasion validation.

synthetic-user-dryrun subagent

Pre-gate multi-persona simulation so live client time isn't burned on an obviously broken pitch.

gate-signoff-validator hook

Blocks the push to /intent/ unless an explicit decision tag and signature block are present.

tracker-sync skill

Automates mapping between Markdown scope blocks and enterprise epic/story schemas.

cleared-intent-trigger

GitHub Action that fires only when the intent.md frontmatter reads gate_status: cleared, instantiating Stage 2 (Design).

Artifact: intent.md (cleared, synced, merged to main) + per-project ESOA (carried forward) + optional Vision Prototype.

Stage 2 · Design — Tactical

Practice

Compressed design session(s), Claude + core engineering leads. Enterprise skills injected into context. Architecture must satisfy the Evidence Gate's operational bounds without over-building beyond intent.md.

Tooling

Figma MCP or repo-native design — design capability doesn't have to live in Figma. Where the capability is confidently prototype-driven, the design system is built directly in Claude Code / Cursor and lives in the repo, feeding spec.md without a Figma round-trip. Choose per project; both paths converge on the same artifact.

.claude/skills/security-baseline

Organization-wide security compliance skill.

.claude/skills/brand-guidelines

Brand compliance skill.

.claude/skills/ux-design-system

UX standards skill.

.claude/skills/adlc-agent-guardrails

Agent behavioral guardrails skill.

spec-compliance-linter

Verifies spec.md has every required section (API specs, failure modes, data models) before the stage can transition.

Artifact: spec.md. Design/Tech Lead review.

Stage 3 · Build — Tactical

Practice

Git worktree isolation (cap 2–3 per engineer). Plan Mode first — Claude writes plan.md before touching source. Engineer accepts the plan, then code generation starts. Scoped Auto Mode execution within defined paths. Deliberately mimics Anthropic's own Build stage — plan mode, CLAUDE.md, subagents, hooks. Sparq-specific tooling layers on top.

Tooling

Claude Code CLI, CLAUDE.md as the repo's context engine.

.claude/agents/verifier.md

Spins up a fresh context window, runs the app, verifies behavior against plan.md.

.claude/agents/simplifier.md

Strips redundant abstraction from generated diffs.

.claude/agents/prompt-evaluator.md

For builds with embedded AI agents — evaluates prompt responses for safety/hallucination/tool-calling accuracy.

path-blocking-hook

Intercepts file edits outside the scope defined in plan.md.

Artifact: plan.md and verified code diffs, in isolated branches. Engineer plan acceptance.

Stage 4 · Test — Tactical

Practice

Agent self-verification (build, unit tests, visual regression) before submission. Non-interactive CI eval suite runs 20–50 task scenarios. Test files are read-only during bug-fix tasks — the agent must fix the code, never weaken the assertion.

Tooling

Headless Playwright/Puppeteer MCP, .github/workflows/agent-evals.yml.

lock-tests.sh hook

Blocks Edit/Write on tests/** during bug-fix tasks.

eval-pass-checker

Blocks PR merge if task accuracy falls below the threshold.

Artifact: verification logs and CI evaluation pass results. Automated CI pass threshold.

Stage 5 · Deploy — Tactical

Practice

Multi-pass PR review (Bugs → Security/PII → spec.md/plan.md compliance). Environment autonomy is tiered: Dev is fully autonomous, Staging requires a clean CI eval run plus automated review, Production requires named human Release Manager sign-off.

Tooling

Claude Code PR Review Agent.

.claude/agents/pr-reviewer.md

Multi-pass review writing findings to REVIEW.md.

Managed-settings engine

allowManagedHooksOnly, permissions.deny, sandboxed shell, disableSideloadFlags, allowManagedMcpServersOnly — matching Anthropic's reference settings.json.

network-egress-blocker hook

Its own named control rather than folded into managed settings generically.

Artifact: REVIEW.md, PR findings, release log. Human Release Manager sign-off on Production only.

Stage 6 · Maintain — Tactical

Practice

Statistical process control on bands.yaml (Western Electric rules). On a breach, a background agent diagnoses root cause and writes a fresh raw intent.md back into Stage 0's triage queue — closing the loop without a human starting it. On-call engineers can also tag Claude directly in incident threads. Every resolved bug becomes a permanent regression case in the Stage 4 eval suite.

Tooling

Infra MCP (Datadog/Prometheus/New Relic) and Product Analytics MCP (PostHog/Mixpanel/Pendo/Zendesk) feeding the same sensor.

metric-watcher daemon

Background monitor triggering triage agents on band breaches.

incident-to-eval-compiler

Turns post-mortem logs into permanent regression tests.

Claude Tag

ChatOps bot for on-call — Anthropic's actual Claude Tag product, not a generic ChatOps MCP Bot.

Artifact: bands.yaml updates, incident records, new regression cases added to Stage 4. Service Owner / on-call triage.

Reconciliation log

Every place the two internal source documents disagreed and the call that was made.

StageConflictCall made
0assumption-extractor (A) vs intent-elicitor + assumption-linter (B)Not a conflict — different functions. Keep all three.
0Workshop length: 60–90 min (both docs)Extended to 2–4 hrs to reflect real client kickoffs.
1Skill named evidence-signal-check (A) vs evidence-synthesizer (B)Canonicalize as evidence-synthesizer.
1Separate confidence-decision.md (A) vs updated intent.md (B)Canonicalize as intent.md updated in place, in the per-project repo alongside the ESOA.
1Old Stage 2 (tracker sync) as its own numbered stageFolded into Stage 1 as a closing action — automatic result of a Promote.
24 compliance skills (A) vs 2 (B)Keep A's full 4; add B's spec-compliance-linter on top.
2Figma-only tooling (both docs)Added repo-native design as an equal path, not a fallback.
3/4Test-lock hook placed at Build (A) vs Test (B)Move to Test — matches Anthropic's own placement.
3prompt-evaluator.md present (A) vs absent (B)Keep — relevant for embedded-AI-agent builds.
5Bundled MDM settings (A) vs split config-engine + network hook (B)Canonicalize on B's split, matches Anthropic's reference settings.json.
6Generic ChatOps MCP Bot (B)Rename to Claude Tag — it's a real, named Anthropic product.

Open gaps vs Anthropic's playbook

CLAUDE.md as governed artifact

Anthropic treats CLAUDE.md with its own feedback loop — the correction goes into CLAUDE.md the second time an agent repeats a mistake, and PR review flags staleness. Neither internal doc gives CLAUDE.md this maintenance loop; it's currently just a context source.

Scheduled security scanning

Anthropic's Deploy stage includes scheduled, model-driven security scanning (Claude Security) running independently of PR review — a recurring scan, not point-in-time, with findings fed back as fresh intent.md. Sparq's only security coverage at Deploy is currently the PR review pass.

Leading/lagging metrics per stage

Anthropic's playbook defines explicit metrics per stage (e.g., time from intent.md commit to spec.md commit; first-pass CI success rate; time from band breach to intent.md in triage). Neither internal doc names how Sparq will measure whether the pipeline itself is working.