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/jircdev/crew-pluginWrote 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/jircdev/crew-plugin/platform)<a href="https://agentmods.dev/agents/jircdev/crew-plugin/platform"><img src="https://agentmods.dev/badge/agents/jircdev/crew-plugin/platform/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/jircdev/crew-plugin/platform"><img src="https://agentmods.dev/badge/agents/jircdev/crew-plugin/platform.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 | $0.00067 | $0.03807 |
| Opus 5.5 | $0.00027 | $0.01523 |
| Sonnet 5.5 | $0.00013 | $0.00761 |
| Haiku 4.5 | $0.00007 | $0.00381 |
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 3d 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 — 169 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.
- 3d ago Changed 1173e83a5d9f
- 8d ago Changed · +4 lines d7009ce73707
- 1mo ago First seen · 165 lines · 67 tokens per session scan A 4ace2ab7e565
platform is an agent published in the GitHub repository jircdev/crew-plugin (1 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 3,807 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
vibe-environment-worker
Runs a vibe session's Vercel environment in symphony-alpha for the vibe and handoff orchestrators. Create mode takes the production flag snapshot in PostHog for the person's real account, pushes the vibe/ branch, starts the environment through the repo's request workflow, follows it to the end, and records the app…
pr-manager
Create/update PR/MR title and description.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
devops-engineer
Handles infrastructure, deployments, database and migrations, environment variables, CI/CD, secrets, and build or runtime troubleshooting. Use proactively for config changes, failed deploys, environment setup, or hardening the pipeline.
devops-automator
Use this agent when setting up CI/CD pipelines, configuring cloud infrastructure, implementing monitoring systems, or automating deployment processes. This agent specializes in making deployment and operations seamless for rapid development cycles. Examples:\n\n \nContext: Setting up automated deployments\nuser: "We…
release-gatekeeper
Nihil release gatekeeper. Audits CI state, versioning, tagging, package publishing, and NuGet trusted-publishing safety before any release. Never approves a release without evidence: a green CI run may publish, a red or unknown run must not. Read-only; returns a gate verdict, never edits or publishes. Use during…