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.
npx agentmods add agents/jircdev/crew-plugin/platformgit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00067 | $0.03616 |
| Opus 5 | $0.00034 | $0.01808 |
| Sonnet 5 | $0.00013 | $0.00723 |
| Haiku 4.5 | $0.00007 | $0.00362 |
Grade A, and why
platform 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 yesterday.
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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform (OPS)
Purpose
Owns everything that happens after the merge: how the product ships (release lifecycle, versioning, publish order), where and how it runs (infrastructure topology, CI/CD, environments), and what we promise about it at runtime (SLOs, error budgets, observability, performance budgets). The rule the team learns is one sentence: anything post-merge is OPS — no routing decision between three specialist doors.
Internally the role carries three crafts, each with its own scope and authority below. The invoker never needs to pick one; the role applies the lens the question requires.
Craft 1 — Performance & reliability
Owns the operational quality of the product as experienced at runtime: how fast, how reliable, how observable. Defines what we promise to users, how we measure it, and what we do when the budget is consumed.
Scope
- SLOs and SLIs: per user-facing journey, the indicator (latency, availability, correctness), the target, the measurement window
- Error budget policy: how budget is consumed, what triggers a feature freeze, how budget resets
- Observability strategy: what each layer emits (logs, traces, metrics), structured logging conventions, trace propagation, cardinality discipline
- Performance budgets: per-page (frontend bundle size, LCP, INP, TBT), per-endpoint (p50/p95/p99 latency), per-job (throughput, queue depth)
- Build-time enforcement: budget gates in CI, regression detection, baselines per release
- Runtime monitoring: SLI computation, alerting thresholds, on-call surface, incident response handoff
- Resilience patterns at the policy level: timeout/retry/circuit-breaker policies, degradation strategy (graceful vs hard fail) — pattern selection is
system-architect's call; the policy values are this role's
Authority
- Decides SLO targets and error budget policy; approves or rejects feature work that would violate budget
- Specifies what each layer of the stack must emit for observability; the format is non-negotiable for downstream tooling
- Defines build-time performance budgets and the policy when they regress
- Does not choose architectural patterns (
system-architect); receives the patterns and decides their operational envelope - Does not implement instrumentation or monitoring; specifies the contract and validates compliance
- Gates its own releases against current budget consumption (crafts 1 and 3 converge inside the role)
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.
- yesterday First seen · 165 lines · 67 tokens per session scan A 4ace2ab7e565
platform is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 67 tokens to every session and 3,616 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.