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 Kyne0328/rel-ai-local-coding-agent --skill rel-ai-workflowgit clone --depth 1 https://github.com/Kyne0328/rel-ai-local-coding-agentWrote 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/kyne0328/rel-ai-local-coding-agent/rel-ai-workflow)<a href="https://agentmods.dev/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-workflow"><img src="https://agentmods.dev/badge/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-workflow/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/kyne0328/rel-ai-local-coding-agent/rel-ai-workflow"><img src="https://agentmods.dev/badge/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 43 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00056 | $0.00943 |
| Opus 5 | $0.00028 | $0.00472 |
| Sonnet 5 | $0.00011 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
rel-ai-workflow 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 9d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rel.AI Workflow
This is the routing skill and the only work-session owner for a repository objective. Open one work_id and keep using it until that objective is completed or explicitly cancelled. Specialized Rel.AI skills reuse the same work session.
Runtime-calibrated workflow
Call relai_work with action: "begin" exactly once. After each successful work-scoped call, treat workflow.recommendedActions as the runtime-calibrated default for what is useful next and workflow.avoidActions as a guard against redundant or over-broad work. Hard runtime errors, authorization, containment, task integrity, and completion gates remain authoritative.
Do not mechanically execute every possible stage. Choose the shortest sufficient path that proves the user's objective:
- Documentation:
begin -> targeted read -> edit -> task-owned review if useful -> finish. - Bugfix:
begin -> reproduce/inspect -> coherent fix -> directly affected check -> task-owned review -> finish. - Feature:
begin -> inspect/design only as needed -> implement coherent slice -> risk-matched checks -> review -> finish. - Investigation:
begin -> search/inspect -> targeted evidence -> report/finish; do not edit unless implementation is requested. - Release:
begin -> inspect release boundary -> focused regression proof -> release-required checks/build/package gates -> review -> finish.
If fresh evidence already proves a recommendation, use the next distinct recommendation instead of repeating the same read, check, review, or process start.
Route only when needed
- Simple localized change with a clear implementation path: stay in this workflow.
- Non-trivial feature, refactor, migration, or dependent multi-stage work: use
rel-ai-planning. - Architecture audit, feasibility study, dependency tracing, or evidence question: use
rel-ai-investigation. - Reproducible error, crash, broken test, regression, or contract failure: use
rel-ai-debugging. - Persistent service, watcher, preview runtime, or interactive CLI: use
rel-ai-dev-process. - Completion proof, release readiness, or explicit final verification: use
rel-ai-verification.
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.
- 9d ago First seen · 52 lines · 56 tokens per session scan A 6d3d5d52e702
rel-ai-workflow is a skill published in the GitHub repository Kyne0328/rel-ai-local-coding-agent (19 stars, last pushed 5d ago), licensed Apache-2.0. It adds 56 tokens to every session and 943 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
codexless-browser-repair
Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…
install-shellby-mcp
Install and verify Shellby MCP on a Mac using terminal access only. Use when a user asks an agent to install, set up, configure, or finish a new Shellby MCP installation from this repository.
trueline-workflow
Use when editing, reading, searching, or exploring files with trueline MCP tools (truelineread, truelineedit, truelinesearch, truelineoutline, truelineverify, truelinechanges). Covers when to pick trueline over built-in Read/Edit/Grep, ref reuse, hash-verified edits, search-then-edit, insertafter semantics, workflows…
spec-governance
A governance skill for managing the lifecycle of specifications: recording intent, routing records, and checking specification changes.
audit-common
A shared baseline audit check covering dimensions named G0G5 and a profile-freshness check. The available description does not explain what those dimensions measure.
cp-gate
A checkpoint workflow for confirming requirements, the proposed solution, and the implementation plan. It uses CP1, CP2, and CP3 in a defined order, with the third checkpoint depending on the type of work.