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 skills add manishiitg/coding-agent-loop --skill engineering-operations-intelligencegit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/skills/manishiitg/coding-agent-loop/engineering-operations-intelligence)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/engineering-operations-intelligence"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/engineering-operations-intelligence/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/skills/manishiitg/coding-agent-loop/engineering-operations-intelligence"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/engineering-operations-intelligence.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 | $0.00019 | $0.00751 |
| Opus 5.5 | $0.00008 | $0.00300 |
| Sonnet 5.5 | $0.00004 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
engineering-operations-intelligence 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 20d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Operations Intelligence
Outcome
Reconcile one team delivery, quality or reliability measure under a versioned rule, then prepare an owner-reviewed improvement question. The broader data model and recurring review guidance remain available; the first route proves one bounded metric and handoff.
When to use
Use when an engineering team wants a reproducible metric linked to an accountable next step. An incident, performance regression or cloud cost exception uses its focused Playbook. Start manually; add recurrence only after a real source-backed case succeeds.
Discovery and user direction
Builder inspects existing Engineering Operations Analyst and Engineering Delivery Coordinator Crews, source authorization, team/service identity, metric definitions and owner policy. Propose reuse or reviewed creation, validator steps, a manual route and a later observation before configuration. Selection starts no issue write or message.
Required inputs
Bind tenant, team, service/repository, metric family and policy revision, distinct item/event identity, source coverage minimum, baseline and current windows, numerator and denominator rules, predeclared target, current issue source and decision owner. Missing coverage or changed definitions stay visible.
Plan and AgentWorks tools
Workflow steps: Analyst reads authorized engineering records and emits engineering-metric-observation/v1 with exact scope, source revisions, count arithmetic, baseline/comparable/not-evaluable state and no causal claim. Run the validator before Delivery. Delivery Coordinator re-reads current issue and ownership state, prepares engineering-improvement-review/v1 bound to the exact observation, and asks the owner to accept, defer or reject a bounded next action. Validate the pair. Issue writes, notifications and deployment are separate reviewed routes with receipts.
Knowledge and persistence
Persist identity joins, source and policy revisions, windows, case key, owner decisions and later observations. Use the operations data model. Changed populations, mappings or metric rules start a new baseline; do not silently rewrite a past result.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/engineering-improvement-review.json 1.5 KB
- examples/engineering-metric-baseline.json 1.2 KB
- examples/engineering-metric-not-evaluable.json 1.2 KB
- examples/engineering-metric-observation.json 1.6 KB
- examples/invalid-engineering-improvement-review.json 1.5 KB
- examples/metric-policy.json 970 B
- examples/review-policy.json 831 B
- examples/source-map.json 1.2 KB
- playbook.json 6.2 KB
- references/data-foundation.md 2.9 KB
- references/metrics-and-findings.md 2.9 KB
- references/recurring-review.md 3.0 KB
- references/team-and-handoffs.md 2.2 KB
- scripts/test_validate_handoff.py 3.9 KB runs code
- scripts/validate_handoff.py 9.8 KB runs code
- SETUP.json 2.7 KB
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.
- 20d ago Changed · -4 lines · -18 tokens per session 77ac437eafb8
- 1mo ago First seen · 53 lines · 37 tokens per session scan A 05ec6560b761
engineering-operations-intelligence is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 19 tokens to every session and 751 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 2026-09-14.
Other skills, from other repositories
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
machinist
Use Machinist to create, assign, and monitor software tasks. Use when a coding agent needs to work with Machinist, its GitHub issue workflow, intake labels, direct runs, or managed queue.
ship-it
Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…
goga-task-by-specifying
Interactive task formulation from a raw request.
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…