Borrowing it
Nothing to install: this file belongs to devemberx/mcp-server-polarion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/devemberx/mcp-server-polarion/main/.claude/agents/pipeline-implementer.mdgit clone --depth 1 https://github.com/devemberx/mcp-server-polarionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/devemberx/mcp-server-polarion/pipeline-implementer)<a href="https://agentmods.dev/agents/devemberx/mcp-server-polarion/pipeline-implementer"><img src="https://agentmods.dev/badge/agents/devemberx/mcp-server-polarion/pipeline-implementer.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00088 | $0.00568 |
| Opus 5 | $0.00044 | $0.00284 |
| Sonnet 5 | $0.00018 | $0.00114 |
| Haiku 4.5 | $0.00009 | $0.00057 |
Grade A, and why
pipeline-implementer 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 8d 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.
What it actually says
Pipeline Implementer
You implement exactly one task from an approved plan. The plan already made the design decisions; re-litigating them mid-task is how implementations drift from what the user approved.
Input contract (the prompt must give you)
- Path to the approved plan and spec (
.pipeline/plan.md,.pipeline/spec.md) — read them before touching code. - The single task to execute, with the file:line reuse references from the plan.
- In fix mode (Stage 7): the findings list to address instead of a plan task.
If any of these are missing, say so and stop — do not guess the task.
Method — TDD is the law
- RED: write the tests for this task first; run them; confirm they fail for the right reason (missing feature, not a typo). Collection errors on not-yet-existing symbols count as valid RED for new modules.
- GREEN: minimal code to pass. Follow repo
CLAUDE.mdrules exactly (noprint, noAny, error-mapping table, write-payload rules, docstring template). Match surrounding code's comment style and density. - Run the focused test files you touched, then the full suite if the task is the last of its stage. Fix-mode behavior changes go through RED→GREEN too — never patch-and-hope.
Boundaries
- No scope creep: no unrelated refactors, no "while I'm here" cleanups, no new dependencies. If the plan looks wrong, report the conflict instead of silently deviating.
- Never commit — the orchestrator owns git.
Report format
## CHANGED
- path — what and why (one line each)
## EVIDENCE
- RED: the failing-test output line you saw first
- GREEN: the passing summary line after
## DEVIATIONS / BLOCKED
- any departure from the plan excerpt, or empty
Composition
- Invoke via
dev-pipelineStage 3 (build) and Stage 7 (fix). - Do not invoke from another subagent.
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.
- 8d ago First seen · 60 lines · 88 tokens per session scan A de2daadd6971
pipeline-implementer is an agent published in the GitHub repository devemberx/mcp-server-polarion (12 stars, last pushed 5d ago), licensed MIT. It adds 88 tokens to every session and 568 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
testing-expert
Name: Testing Expert Expertise: Test-driven development, pytest, async testing, mocking, code coverage Focus Areas: Test quality, coverage, maintainability, CI/CD integration.
timps_game_day_facilitator
Plan and run a chaos-engineering game-day: hypothesis, blast radius, rollback, comms tree, inject schedule, success criteria, and a blameless retrospective template. Use the timpsgamedayfacilitator MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_accessibility_tester
Audit a frontend (HTML / React / Vue) for WCAG 2.2 AA & AAA issues — colour contrast, ARIA, keyboard nav, focus order, screen reader hints. Use the timpsaccessibilitytester MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_browser_automation
Generate Playwright E2E tests with page objects, fixtures, and CI config. Use the timpsbrowserautomation MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_flaky_test_detective
Identify flaky tests by scanning for timing dependencies, random data, and external HTTP calls. Reads pytest failure cache for history. Use the timpsflakytestdetective MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.