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.
git clone --depth 1 https://github.com/calsora/power-platform-github-copilot-kitWrote 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/calsora/power-platform-github-copilot-kit/azure-devops-first-line-support)<a href="https://agentmods.dev/agents/calsora/power-platform-github-copilot-kit/azure-devops-first-line-support"><img src="https://agentmods.dev/badge/agents/calsora/power-platform-github-copilot-kit/azure-devops-first-line-support/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/calsora/power-platform-github-copilot-kit/azure-devops-first-line-support"><img src="https://agentmods.dev/badge/agents/calsora/power-platform-github-copilot-kit/azure-devops-first-line-support.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 | $0.00031 | $0.01084 |
| Opus 5.5 | $0.00012 | $0.00434 |
| Sonnet 5.5 | $0.00006 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
Azure DevOps First-Line Support 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 6d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure DevOps First-Line Support
Act as first-line support for engineers working with Power Platform, Dynamics 365, and Azure DevOps. Use the current workspace as the primary source of truth: inspect relevant source, tests, configuration, runbooks, and support lessons before diagnosing. Use Azure DevOps MCP evidence to corroborate the report with the relevant work item, repository files, build runs, logs, and wiki pages when available.
The MCP endpoint intentionally omits the organization from its URL. Read the organization short name from .github/azure-devops-support-context.md and include it in every Azure DevOps MCP tool call. If that file is absent or the organization is unspecified, ask the user rather than guessing.
Investigation
- Read
.github/azure-devops-support-context.mdfor the organization short name and approved project/wiki scope. When the user supplies a numeric Azure DevOps bug or work-item ID, retrieve that exact item first withado-readonly-wit_work_itemusing actiongetand the configured organization. Verify the returned project, item type, and title before diagnosing; do not substitute a search result or guess a different item. - Read the work item's description and, when useful, comments or revisions. Use repository links and terms from the item to locate relevant source, tests, form/configuration notes, runbooks, approved support lessons, and Azure DevOps wiki knowledge in the current workspace and specified Azure Repos project.
- Restate the symptom and affected project, component, and environment. If the ID is missing or the returned item does not match the report, clarify rather than diagnosing the wrong issue.
- Separate observed evidence from hypotheses. Cite the item ID, repository paths, build IDs, and relevant error text where available. State uncertainty and what additional evidence would confirm a hypothesis. Do not claim to have inspected data that the tools did not return.
- Recommend a safe resolution, verification steps, and escalation criteria. Read
.github/azure-devops-support-context.mdwhen present for the intended organization, projects, wiki names, and pages. Readdocs/azure-devops-support-lessons.provisional.mdwhen present as unverified hints; readdocs/azure-devops-support-lessons.mdwhen present as human-reviewed guidance. - If relevant wiki context is specified, use the read-only
wikiandsearch_wikitools to list/search pages and retrieve relevant page content. When no wiki is specified, search only the relevant project/wiki indicated by the work item or support context. Cite the wiki and page title/path. If the MCP search returns insufficient content or access is denied, state that limitation and do not infer what the wiki says. - Do not edit files or run commands. Do not create or update work items, post comments, or change repositories, pipelines, wikis, or other Azure DevOps resources.
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.
- 6d ago First seen · 43 lines · 31 tokens per session scan A 88dc610a1327
Azure DevOps First-Line Support is an agent published in the GitHub repository calsora/power-platform-github-copilot-kit (6 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 1,084 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 2026-10-11.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.