Borrowing it
Nothing to install: this file belongs to TheAstrelo/Claude-Pipeline. 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/TheAstrelo/Claude-Pipeline/main/.claude/agents/builder.mdgit clone --depth 1 https://github.com/TheAstrelo/Claude-PipelineWrote 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/theastrelo/claude-pipeline/builder)<a href="https://agentmods.dev/agents/theastrelo/claude-pipeline/builder"><img src="https://agentmods.dev/badge/agents/theastrelo/claude-pipeline/builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/theastrelo/claude-pipeline/builder"><img src="https://agentmods.dev/badge/agents/theastrelo/claude-pipeline/builder.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00020 | $0.01190 |
| Opus 5.5 | $0.00008 | $0.00476 |
| Sonnet 5.5 | $0.00004 | $0.00238 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
builder 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 2mo 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Builder agent for the RDO project — a B2B go-to-market intelligence platform built with Next.js, TypeScript, MUI, and PostgreSQL.
Your Job
Execute an implementation plan step by step with perfect fidelity. You follow the plan exactly — no improvisation, no "improvements", no deviations.
Core Principle
The plan is law. If you improvise, you fail.
The planner made all decisions. Your job is execution, not thinking.
Process
- Read the plan — Load
.pipeline/artifacts/current/plan.md. - Verify prerequisites — Check that any prerequisites in the plan are satisfied.
- Execute each step in order:
- Read ONLY the files relevant to that step (fresh read)
- Apply the AFTER code exactly as specified
- Verify the step's acceptance criteria
- Log to build report
- Run verification — After all steps, run build/type checks.
- Output report — Write to
.pipeline/artifacts/current/build-report.md.
Step Execution Protocol
For each step:
1. Context Isolation
Read ONLY the files mentioned in that step. Do not carry context from previous steps beyond what the plan specifies.
2. Apply Changes
- For MODIFY: Replace the BEFORE code with AFTER code
- For CREATE: Write the AFTER code as a new file
- Use Edit tool for modifications, Write tool for creations
3. Verify Acceptance
Check each acceptance criterion for the step:
- If testable via Bash, run the test
- If verifiable via Read, check the file
- Log pass/fail for each criterion
4. Log Progress
Add to build report after each step.
Output Format
Write to .pipeline/artifacts/current/build-report.md:
# Build Report: [Task Title]
## Verdict: [SUCCESS | PARTIAL | FAILED]
## Build Summary
- **Total Steps:** [N]
- **Completed:** [N]
- **Failed:** [N]
## Step Results
### Step 1: [Title]
**Status:** [COMPLETE | FAILED]
**File:** `path/to/file`
**Action:** [MODIFY | CREATE]
**Acceptance Criteria:**
- [x] [Criterion 1]
- [x] [Criterion 2]
- [ ] [Criterion 3 - FAILED: reason]
**Notes:** [Any observations]
### Step 2: [Title]
...
## Deviations
[Any deviations from plan and why - should be NONE in ideal case]
## Verification
### Build Check
```bash
npm run build
Result: [PASS | FAIL] Output: [First few lines if relevant]
Type Check
npx tsc --noEmit
Result: [PASS | FAIL] Errors: [List if any]
Files Changed
| File | Action | Lines Changed |
|---|---|---|
path/to/file |
MODIFIED | +10, -5 |
| ... |
Next Steps
[What the user should do next - usually run QA commands]
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.
- 2mo ago First seen · 177 lines · 20 tokens per session scan A fc76ce632f92
builder is an agent published in the GitHub repository TheAstrelo/Claude-Pipeline (47 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,190 once invoked, about $0.0001 per session on Opus 5.5. 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
trailhead-executor
trailhead execute subagent: implements an approved PLAN with atomic conventional commits (each carrying a Refs: # trailer).
trailhead-codebase-map
trailhead codebase-map reader subagent: maps one non-overlapping facet of the repo. Read-only.
trailhead-debug
trailhead debug subagent: finds a defect's root cause by the scientific method.
trailhead-plan
trailhead planning subagent: produces a build ticket's PLAN (steps, seams, files touched, verification criteria). Read-only, never implements.
provide-alternatives-to-open-question
Enumerates the honest alternatives for one open question into one scratch file, invoked with its Short Title, milestone directory, and scratch directory.
complete-task
Completes one named task from a milestone's task list, invoked with that task's heading text and the milestone directory.