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 api-performance-validationgit 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/api-performance-validation)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/api-performance-validation"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/api-performance-validation/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/api-performance-validation"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/api-performance-validation.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 | $0.00040 | $0.00706 |
| Opus 5.5 | $0.00016 | $0.00282 |
| Sonnet 5.5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
api-performance-validation 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Performance Validation
Outcome
Create a repeatable API performance workflow that exercises approved scenarios under bounded load, evaluates customer budgets, preserves comparable samples, and reports supported latency, throughput, reliability, and capacity findings.
When to use
Use for service-level performance baselines, regressions, release checks, or controlled capacity experiments. Require explicit authorization before meaningful load; production is never assumed to be an acceptable target.
Discovery and user direction
Inspect the current workflow, goals, metrics, configuration, capabilities, stores, reports, and triggers before proposing changes. Summarize reusable design and gaps, then ask focused questions for unresolved customer choices such as scope, success, approvals, thresholds, ownership, and budgets. Record the answers as customer direction. Installation alone does not approve workflow changes or execution. Default to one small-team workflow; split only for incompatible access or lifecycle boundaries.
Required inputs
Resolve endpoints and protocol, environment/build, authentication and secret references, scenarios/payload classes, test-data cleanup, load shape, worker location, connection behavior, sample duration, budgets/baseline, stop limits, observability access, evidence retention, and owner.
Plan and AgentWorks tools
Use scripted steps for preflight, the saved load runner, deterministic parsing, aggregation, persistence, and policy decisions. Use a message sequence to correlate supported regressions with metrics/traces. Persist high-load or state-changing proposals for durable review, end preparation, and let a separate execution route validate the saved approval and exact target before sending traffic.
Knowledge and persistence
Store policies, profiles, scenarios, runs, samples, aggregates, errors, and findings in durable tables. Store sanitized runner output, request summaries, traces, and profiles in durable assets. Keep secret values and unrestricted bodies out of artifacts; add only verified non-sensitive service facts to KB notes.
What ships with it
3 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.
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 · 51 lines · 40 tokens per session scan A 1edc3fca5490
api-performance-validation is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 40 tokens to every session and 706 once invoked, about $0.0002 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
fiber-rest-api
Use when adding or changing a Go HTTP endpoint — Fiber v2 or v3 (detect which), thin handlers, central error mapping, boundary validation; the same rules apply to net/http, chi, echo or gin.
go-hexagonal-architecture
Use when adding a use case, port, repository or adapter in a Go service — where each piece goes, how errors and transactions cross layers, and how to check the import direction.
zerolog-observability
Use when adding logging to Go code - the repository's logger with structured fields, request-scoped correlation, correct levels, no secrets or double-logging.
backend-language-decision
Use when starting a backend task that could be built in more than one language - follow the repository's stack, or for a greenfield service choose between Go, Java, C#/.NET, TypeScript on Node.js and Rust from the task's shape.
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
go-add-entity
Add a full CRUD vertical slice (domain, DTO, repository, service, handler, migration, factory wiring) to an existing GOB Go microservice.