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/nitin27may/e-commerce-agents/readmegit clone --depth 1 https://github.com/nitin27may/e-commerce-agentsWrote 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/nitin27may/e-commerce-agents/readme)<a href="https://agentmods.dev/agents/nitin27may/e-commerce-agents/readme"><img src="https://agentmods.dev/badge/agents/nitin27may/e-commerce-agents/readme.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01018 |
| Opus 5 | $0.00000 | $0.00509 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade B, and why
README scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
collaborator's `~/.claude/settings.json` model, but a per-session `/model` (or How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code model strategy & subagents
This repo configures Claude Code in two layers. The split between "plan on Opus,
build on Sonnet" is a session-model concern, not a subagent concern — so it lives
in settings.json, and the subagents below cover the other activities where a
different model genuinely helps.
Layer 1 — session model (.claude/settings.json)
{ "model": "opusplan" }
opusplan runs Opus while in Plan mode and Sonnet for normal interaction and
implementation. That is the entire "planning → Opus, coding → Sonnet" requirement,
done at the level that actually controls it.
Why not do this with a subagent? A subagent's model: field only governs work that
Claude delegates to that subagent. It does not govern Plan mode or the main
implementation loop — those run on the session model. So no .claude/agents/*.md
setting can make "planning use Opus while coding uses Sonnet"; opusplan is the
correct mechanism.
Caveats (read these)
- Opus access required.
opusplanneeds Opus entitlement (Claude Max, or API/Enterprise). On the Pro plan Opus is unavailable and this setting won't engage. - This is a checked-in default, not a lock. Project
settings.jsonoverrides a collaborator's~/.claude/settings.jsonmodel, but a per-session/model(or--model/ANTHROPIC_MODEL) still wins. Anyone who can't use Opus can override with/model sonnet. To make it personal instead of shared, move themodelkey into.claude/settings.local.json(gitignored). - Env vars silently win. Session model precedence is roughly
/model>--model>ANTHROPIC_MODELenv > settings file. Subagent model precedence isCLAUDE_CODE_SUBAGENT_MODELenv > per-invocation > frontmatter > main model. If you exportANTHROPIC_MODELorCLAUDE_CODE_SUBAGENT_MODELanywhere in your shell profile, it overrides everything here. - No 1M context in the plan phase. The automatic 1M-context upgrade applies to
the plain
opussetting, notopusplan— the plan-mode Opus phase uses the standard context window. For planning against very large contexts, prefer a manual/model opussession. - Aliases vs pinned IDs. The agents below use aliases (
opus,sonnet,haiku). To pin versions, swap an alias for a full ID (claude-opus-4-8,claude-sonnet-4-6,claude-haiku-4-5-20251001).opusplanitself cannot be pinned — pinning means managing the plan/code split manually.
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.
- 4d ago First seen · 72 lines · 0 tokens per session scan B dd77af50bc98
README is an agent published in the GitHub repository nitin27may/e-commerce-agents (21 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,018 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
anvil-quality-reviewer
Hostile maintainability reviewer. Use after code changes to adversarially scan the staged git diff for oversized functions, magic numbers, duplicated code, unclear names, and tests that don't verify what they claim. Quotes the exact offending lines.
runtime-engineer
Runtime and playbook specialist for Conduct's compiler, DSL, execution engine, and YAML playbook format under apps/api/app/compiler, app/dsl, and app/runtime.
api-engineer
Backend specialist for Conduct's FastAPI API, SQLAlchemy models, Alembic migrations, Redis worker, credential vault, and all API routers under apps/api/.
frontend-engineer
Frontend specialist for Conduct's Next.js canvas UI, run feed, settings pages, and all components under apps/web/.
rundock-guide
Helps you set up and navigate your Rundock workspace. Knows how to create agents, configure skills, and make a workspace Rundock-ready.
hive-reviewer
Forge task assurance specialist validating that completed work satisfies the originating wish with uncompromising rigor.