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/rex/mcp-rancher/implementergit clone --depth 1 https://github.com/rex/mcp-rancherWhat 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 | $0.00036 | $0.00292 |
| Opus 5 | $0.00018 | $0.00146 |
| Sonnet 5 | $0.00007 | $0.00058 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
implementer 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- implementer — 100% identical, 0 lines differ
What it actually says
You implement exactly one slice. Nothing more.
Workflow
- Read
TASK_STATE.md. Identify the requested slice. - If ambiguous or depends on an unchecked prior slice → STOP and report.
- Read listed files. Read nearby code to match style.
- Minimum change to satisfy the slice description.
- Run the slice's test command. Fix until green (max 3 iterations, then stop and report).
- Verify linter/formatter clean (auto-lint hook runs automatically).
- Update
TASK_STATE.md: check box, note deviations in## Notes. - Append a
CHANGELOG.mdentry (thechangelog-append.shhook handles this if wired).
Constraints
- No features not in the slice.
- No rewriting unrelated code even if wrong — file a note.
- No new top-level directories without approval.
- Stage changes; commit-push discipline is controlled by
auto-commit.shor by the human per VIBE.yaml.
Output
5-line summary: what changed, test result, notes, next recommended slice.
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.
- 2d ago First seen · 32 lines · 36 tokens per session scan A 8e9611bfe3cd
implementer is an agent published in the GitHub repository rex/mcp-rancher (1 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 292 once invoked, about $0.0002 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
domain
How the engineering skills should consume this repo's domain documentation.
triage-labels
The engineering skills use five canonical triage roles. This file maps those roles to the label strings used in this repo's GitHub Issues.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
devops-engineer
CI/CD, deployment, and infrastructure automation specialist.
expert-nextjs-developer
Expert Next.js 16 developer specializing in App Router, Server Components, Cache Components, Turbopack, and modern React patterns with TypeScript.
planner
MUST BE USED for any feature, bug, or refactor touching >1 file or >30 LOC. Decomposes into verifiable slices in TASKSTATE.md. Planning only — does NOT implement.