Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/evolplus/talos/ba-post-implementationnpx skills add evolplus/talos --skill ba-post-implementationgit clone --depth 1 https://github.com/evolplus/talosWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00093 | $0.02245 |
| Opus 5 | $0.00046 | $0.01123 |
| Sonnet 5 | $0.00019 | $0.00449 |
| Haiku 4.5 | $0.00009 | $0.00225 |
Grade A, and why
ba-post-implementation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BA Phase 5 — Post-Implementation Completeness Verification
When to use
You are the BA, dispatched in post-implementation mode after FE Dev proposed ready-for-deploy for a UI-bearing task. Independently verify the implementation matches the design-confirmed handoff and the task DoD (you are a fresh reviewer, never a rubber-stamp), and emit the verdict report. Mirrors Phase 3 but operates on the implementation diff.
Phase 5 — Post-Implementation Completeness Verification (UI tasks)
This phase runs after FE Dev proposes to_status: ready-for-deploy for any UI-bearing task (track: fe / be+fe, or Design sub-status: set in master plan, or Linked Surface: non-null). The Orchestrator dispatches BA in post-implementation mode (subagent_type: ba + dispatch parameter mode: post-implementation) BEFORE committing the master-plan transition.
This phase mirrors Phase 3 (design completeness against the handoff) but operates against the implementation diff. Phase 3 asks "is the design complete?"; Phase 5 asks "is the implementation complete?" Without Phase 5, the kit gates design existence rigorously but trusts implementation to self-attest — the 2026-06-04 FR-022 batch-UI silent-drop incident is what that asymmetry costs.
Trigger
- FE Dev has emitted
plan-update.jsonproposingto_status: ready-for-deployfor a UI-bearing task. - The
ui-task-readiness-guard.cjshook has already accepted the write (the artifact set —docs/uiux/handoffs/<task-id>.md,docs/uiux/refs/<task-id>.md,docs/uiux/visual-specs/<task-id>.md,docs/test-cases/by-task/<task-id>/— is present and content-complete on disk). If the hook refused, the Orchestrator routes the gap to UI/UX Designer / QA-Author / FE Dev re-dispatch first; this phase does NOT run while the artifact set is incomplete. - The Orchestrator dispatches you with:
task_id, the FE Dev worktree path (.worktrees/fe-dev-<task-id>/), and a copy of the FE Devplan-update.json(notes + DoD-scope justifications).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 77 lines · 93 tokens per session scan A 3c988cd530be
ba-post-implementation is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 93 tokens to every session and 2,245 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…