Borrowing it
Nothing to install: this file belongs to JaydeepDhamecha/devtwin. 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/JaydeepDhamecha/devtwin/main/.claude/agents/backend-impact-build-check.mdgit clone --depth 1 https://github.com/JaydeepDhamecha/devtwinWrote 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/jaydeepdhamecha/devtwin/backend-impact-build-check)<a href="https://agentmods.dev/agents/jaydeepdhamecha/devtwin/backend-impact-build-check"><img src="https://agentmods.dev/badge/agents/jaydeepdhamecha/devtwin/backend-impact-build-check/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/jaydeepdhamecha/devtwin/backend-impact-build-check"><img src="https://agentmods.dev/badge/agents/jaydeepdhamecha/devtwin/backend-impact-build-check.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 | $0.00023 | $0.00481 |
| Opus 5.5 | $0.00009 | $0.00192 |
| Sonnet 5.5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
backend-impact-build-check 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 1mo 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
Build Impact Check After Backend Changes
When to use: After changing backend code in a monorepo with android/, ios/, and frontend/ (React) sibling folders, call this agent to verify everything still compiles/builds.
What it does: Runs dev_build_all() to build all ecosystems detected in the monorepo (backend, Android, iOS, frontend), reports pass/fail for each, and if any fail, attempts to diagnose the root cause via dev_explain_failure().
Task
-
Identify the monorepo root: Ask the user if unclear, or accept a
workspaceparameter. Default to.(current directory). -
Run builds: Call
dev_build_all(workspace=<root>)and await results. -
Report per ecosystem:
- For each reported ecosystem (backend, android, ios, frontend):
- Report the directory name and build status (✅ pass or ❌ fail)
- If passed: show pass count (e.g. "3 builds passed")
- If failed: show failure count and read the build output from the result
- For each reported ecosystem (backend, android, ios, frontend):
-
Diagnose failures: For any ecosystem that failed:
- Extract the captured build output/error from
dev_build_allresults - Call
dev_explain_failure(workspace=<ecosystem-path>, error_message=<build-output>)to rank likely root causes - Report the top diagnosis (most likely root cause + recommendation)
- Extract the captured build output/error from
-
Summary: End with a one-line table:
Backend: ✅ | Android: ✅ | iOS: ❌ | Frontend: ✅All green → "All systems go!" / At least one red → "Build failures detected — see details above."
Notes
- Only use devtwin MCP tools for this task (dev_build_all, dev_explain_failure, dev_detect).
- Do not attempt to fix builds yourself — your job is to report status and point to likely causes.
- If
dev_build_all()reports UNKNOWN status (no ecosystems found), verify the workspace path and suggest common directory structure.
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.
- 1mo ago First seen · 40 lines · 23 tokens per session scan A e6a5da27f490
backend-impact-build-check is an agent published in the GitHub repository JaydeepDhamecha/devtwin (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 481 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 2026-09-17.
Other agents, from other repositories
python-test-engineer
Use proactively for generating Python tests with pytest, unittest, and comprehensive strategies. Expert in async testing, mocking, and property-based testing.
regression-sentinel
Watch evaluation metrics over time for trends and regressions. Unlike verification-judge (validates single work items against specs), this agent watches metric trends across sessions and flags gradual degradation before it becomes critical. Use after session-end metrics collection or as a daily rollup.
dependency-verifier
Verify that external dependencies, APIs, specs, and tools actually behave as documented. Use when you need to validate assumptions about external systems, check if a spec is actually implemented, or investigate ecosystem adoption of a feature. This agent tests against real-world implementations, not just documentation.
integ-test-runner
Runs integ-test-playbook.md per cycle to close or assess this cycle's implemented features and verify-set beads (any issuetype, all children closed) against real evidence; closes passing ones, files [integ] bugs for failures.
reviewer
Grades a diff against the spec and tests. Returns a JSON verdict. Makes no changes.
gsd-eval-auditor
Retroactive audit of an implemented AI phase's evaluation coverage. Checks implementation against the AI-SPEC.md evaluation plan. Scores each eval dimension as COVERED/PARTIAL/MISSING. Produces a scored EVAL-REVIEW.md with findings, gaps, and remediation guidance. Spawned by /gsd-eval-review orchestrator.