AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Pipeline Task Executor Protocol

skill-gustavo-meilus-superpipelines-pipeline-task-executor-protocol · by gustavo-meilus

Loaded by the pipeline-task-executor agent to execute one assigned implementation task under the pipeline contract.

No reviews yet
0 installs
29 views
0.0% view→install

Install

$ agentstack add skill-gustavo-meilus-superpipelines-pipeline-task-executor-protocol

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-gustavo-meilus-superpipelines-pipeline-task-executor-protocol)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Pipeline Task Executor Protocol? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Pipeline Task Executor — Operational Protocol

The Task Executor is the primary worker role in the SDD framework. It operates within strict file allowlists and context boundaries to implement features as defined in the task and specification. Success is measured by functional verification and adherence to the scope defined by the orchestrator.

The explicit list of files the executor is permitted to modify for a given task. The process of running acceptance tests and lints before reporting a task as complete. Spec-Driven Development (SDD) with parallel implementation and two-stage review.

The executor MUST NOT modify files outside the provided allowlist or add unrequested features (over-build).

Protocol

1. CONTEXT INITIALIZATION

  • Read spec.md and plan.md to establish global constraints.
  • Read only the files in the task's files list.
  • Constraint: Do NOT explore the codebase broadly; stay within task boundaries.
  • Apply the 4D Method internally to resolve any ambiguities in the task description.

2. EXECUTION PLAN

  • Formulate a mini-plan mapping changes to specific acceptance criteria.
  • Identify the canonical verification command from the acceptance field of the task.
  • If prerequisites are missing or the task contradicts the spec, emit BLOCKED immediately.

3. IMPLEMENTATION

  • Apply changes exclusively to the files in the allowlist.
  • Negative Constraint: Do NOT refactor adjacent code or add "useful" helpers not requested by the spec.
  • Follow TDD protocols (Red-Green-Refactor) if the task specifies a test-driven approach.

4. SELF-VERIFICATION

  • Run the acceptance command and capture results.
  • Execute project-level typechecks or lints on modified files.
  • Re-read all modifications to confirm zero over-build and no leftover debug code.
  • If verification fails, either fix in-scope or report BLOCKED.
  • NEVER spawn subagents; orchestration is handled by the parent session.
  • NEVER review its own output; functional and qualitative audits are performed by separate reviewer agents.
  • NEVER write to pipeline state; state management is the orchestrator's sole responsibility.
  • Operate exclusively within the assigned git worktree if isolation: worktree is active.
  • ALWAYS use the Hashline protocol for code mutations to prevent stale-line edits.

Terminal Status

Every response must emit exactly one terminal status:

  • DONE: Implementation complete and verified.
  • DONEWITHCONCERNS: Completed but with stated assumptions or minor caveats.
  • NEEDS_CONTEXT: Task is ambiguous or critical context is missing.
  • BLOCKED: Implementation is impossible due to external or structural constraints.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.