Borrowing it
Nothing to install: this file belongs to Nam-Cheol/namba-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Nam-Cheol/namba-ai/main/.agents/skills/namba/SKILL.mdgit clone --depth 1 https://github.com/Nam-Cheol/namba-aiWrote 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/nam-cheol/namba-ai/namba)<a href="https://agentmods.dev/skills/nam-cheol/namba-ai/namba"><img src="https://agentmods.dev/badge/skills/nam-cheol/namba-ai/namba/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/nam-cheol/namba-ai/namba"><img src="https://agentmods.dev/badge/skills/nam-cheol/namba-ai/namba.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 | $0.00018 | $0.01869 |
| Opus 5 | $0.00009 | $0.00934 |
| Sonnet 5 | $0.00004 | $0.00374 |
| Haiku 4.5 | $0.00002 | $0.00187 |
Grade A, and why
namba 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 10d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill whenever the user mentions namba, namba help, namba project, namba regen, namba update, namba codex access, namba plan, namba harness, namba fix, namba run, namba queue, namba sync, namba pr, namba land, namba release, $namba-help, $namba-coach, $namba-create, $namba-queue, $namba-plan-review, $namba-review-resolve, $namba-release, or asks to use the Namba workflow.
Generated instruction contract for this repo skill:
- Purpose: keep the role or command scope explicit, bounded, and testable.
- Boundary: honor read-only versus mutating state effects, configured sandbox mode, and assigned file or workflow ownership.
- Required output: report concrete actions, changed paths or artifacts, validation evidence, and pass/fail status or blockers.
- Pass/fail criteria: claim success only when acceptance criteria and configured validation are satisfied; otherwise name the exact blocker and impact.
- Evidence expectations: cite source artifacts such as SPEC files,
.namba/configs, diffs, test output, PR/check links, or generated manifests instead of relying on unsupported assertions. - Security responsibilities: never expose or commit secrets; treat auth, privacy, destructive commands, permission changes, and external network or credential use as security-sensitive.
- Destructive command and escalation policy: do not run destructive commands unless explicitly requested; request approval for privileged, networked, or sandbox-blocked actions only when the active approval mode allows it, and otherwise report the blocker or use a safe non-escalating path.
- Fallback implementer boundary: if a specialist path is unavailable and the main/default implementer takes over, stay within the assigned scope and preserve the same evidence and validation duties.
- Portability: keep durable guidance non-project-specific unless the current repository config or SPEC explicitly provides the project detail.
Command mapping:
$namba-help: explain how to use NambaAI in this repository, which command or skill to use next, and where the authoritative docs live, without mutating repository state.$namba-coach: restate the user's current goal, ask only essential routing questions when needed, correct clearly wrong command choices, and hand off to exactly one primary Namba workflow invocation without mutating repository state.$namba-create: run the skill-first creation workflow for repo-local skills, project-scoped custom agents, or both. Keep the user-facing surface inside Codex and do not add a publicnamba createCLI command in this slice.namba project: refresh repository docs and codemaps.namba codex access: inspect or update Namba runnercodex execaccess defaults with explicitapproval_policy/sandbox_modeflags; repo.codex/config.tomldoes not persist interactive approval or sandbox choices.namba regen: regenerate AGENTS, repo-local skills, command-entry skills, Codex custom agents, readable role cards, and repo-local Codex config from.namba/config/sections/*.yaml.namba update [--version vX.Y.Z]: self-update the installednambabinary from GitHub Release assets only after explicit user approval.namba plan "<description>": create the next feature SPEC package under.namba/specs/, and when branch-per-work is enabled create or switch to the dedicatedspec/...branch in the current workspace; unless--no-reviewis present, continue immediately with$namba-plan-review SPEC-XXXafter creation.$namba-plan-review: create or resolve a SPEC, run the three plan-review tracks in parallel when possible, and drive the advisory readiness loop before implementation starts.namba harness "<description>": create the next harness-oriented SPEC package under.namba/specs/through the same dedicated-branch planning contract for reusable agent, skill, workflow, or orchestration work.$namba-plan-pm-review/$namba-plan-eng-review/$namba-plan-design-review: update product, engineering, or design review artifacts under.namba/specs/<SPEC>/reviews/and refresh advisory readiness.namba fix --command plan "<issue description>": create the next bugfix SPEC package under.namba/specs/through the same dedicated-branch planning contract.namba fix "<issue description>"ornamba fix --command run "<issue description>": perform direct repair in the current workspace without creating a SPEC package.$namba-review-resolve: resolve the target PR from the current branch when possible, inspect unresolved review threads with thread-aware GitHub state, record thread identity and outcome, validate before replying or resolving, include CI/check evidence when relevant, and avoid duplicating the configured review marker.$namba-release: draft release notes from commits since the previous semver tag, write the notes to a durable per-version artifact, then hand off to the guardednamba release --version <version> --pushpath with a GitHub Release body that uses the generated notes.namba run SPEC-XXX: execute the SPEC in the current Codex session. Readspec.md,plan.md, andacceptance.md, implement directly, validate, and sync artifacts.namba run SPEC-XXX --solo|--team|--parallel: use the standalone CLI runner when you need explicit single-subagent, multi-subagent, or worktree-parallel execution semantics.namba queue start <SPEC-RANGE|SPEC-LIST>: process already-existing SPEC packages one at a time through review, run, PR, checks, optional land, and local main refresh. Usestatus,resume,pause, andstopto operate the durable queue.namba sync: refresh change summary, PR checklist, codemaps, advisory review readiness, and PR-ready docs after implementation.namba pr "<title>": run sync plus validation by default, inspect PR checks, summarize bounded GitHub Actions failure snippets when checks fail, commit and push the current branch, and create or reuse a PR without requesting Codex review.namba pr --review "<title>": perform the same PR handoff and explicitly request Codex review with the configured marker exactly once.namba land: resolve the current branch PR, optionally wait for checks, merge when the PR is clean, and update localmainsafely.namba doctor: verify that AGENTS, repo skills,.nambaconfig, Codex CLI, and the globalnambacommand are available.
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.
- 10d ago First seen · 54 lines · 18 tokens per session scan A 883532ea94f5
namba is a skill published in the GitHub repository Nam-Cheol/namba-ai (11 stars, last pushed 17d ago), licensed MIT. It adds 18 tokens to every session and 1,869 once invoked, about $0.0001 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
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
docs-update-from-diff
Review local code changes with git diff and update the official docs under docs/ to match. Use when the user asks to document current uncommitted work, sync docs with local changes, update docs after a feature or refactor, or when phrases like "git diff", "local changes", "update docs", or "official docs" appear.
prepare-pr
Prepare GitHub pull request title and body files from the current branch diff, especially for non-interactive CI/autofix flows that must follow the repository PR template without pushing or creating the PR.
triage
Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.
git-revert-safety
Apply when reverting commits, undoing merges, or recovering from branch contamination. Covers collateral damage verification (manifest, package.json, CHANGELOG, lockfiles), cherry-pick vs revert decision matrix, partial-revert detection, merge-parent handling, and post-revert CI verification. Prevents the most common…