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 skills/bkper/bkper-cli/skillnpx skills add bkper/bkper-cli --skill skillgit clone --depth 1 https://github.com/bkper/bkper-cliWhat 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 | $0.00051 | $0.01893 |
| Opus 5 | $0.00026 | $0.00946 |
| Sonnet 5 | $0.00010 | $0.00379 |
| Haiku 4.5 | $0.00005 | $0.00189 |
Grade A, and why
bkper-cli 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bkper Context
You are helping with Bkper.
Protect the zero-sum invariant above all else.
Use this skill when an external coding-agent harness needs to understand Bkper, operate the local bkper CLI safely, work with Bkper SDKs, build Bkper apps, or reason about Bkper financial/accounting flows.
IMPORTANT Operating Principles
- Interview the user about every aspect of the plan until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
- Ask the questions one at a time.
- If a question can be answered by exploring the codebase, explore the codebase instead.
- Only perform mutating actions (creating/editing files, destructive shell commands, API writes) when the user has explicitly requested that change in the current turn. When exploring, debugging, or unsure, propose the change and wait for confirmation instead of acting.
- Treat any
bkperCLI command that writes to a Book (transactions, accounts, groups, books, collections, apps, imports, batch ops) as irreversible: show the exact command and wait for explicit user confirmation before running it. Read-only commands (list, get, balances, search, export) need no confirmation. - For AI-derived transactions, always send
draft: trueto bypass Book auto-posting; never post them without explicit human approval. - For accounting numbers — balances, statements, reconciliations, taxes — never let raw LLM output be final; use or establish a deterministic, auditable route, keep computation separate from commentary, and make assumptions explicit.
- Think in resources, movements, and balances — not debits and credits.
- Extend meaning with properties before adding structural complexity.
- Model domain and flows before coding; represent business reality, not technical shortcuts.
- Prefer simplicity over cleverness; choose small, boring, maintainable solutions.
Skill Purpose
This skill is for external coding-agent harnesses — Claude Code, Codex, OpenCode, OpenClaw, Hermes Agent, Cursor, and similar tools — when they can use local tools and shell commands.
What ships with it
23 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.
- references/advisory/accountant-recommendations.md 7.8 KB
- references/apps/ai.md 11 KB
- references/apps/app-listing.md 3.3 KB
- references/apps/architecture.md 9.0 KB
- references/apps/configuration.md 8.7 KB
- references/apps/context-menu.md 4.7 KB
- references/apps/deploying.md 4.8 KB
- references/apps/development.md 4.9 KB
- references/apps/event-handlers.md 8.9 KB
- references/apps/first-app.md 3.6 KB
- references/apps/overview.md 6.6 KB
- references/apps/quality.md 4.7 KB
- references/apps/security.md 3.1 KB
- references/apps/self-hosted.md 3.5 KB
- references/apps/shared-app-source.md 4.6 KB
- references/cli/app-management.md 26 KB
- references/cli/data-management.md 25 KB
- references/core/core-concepts.md 8.7 KB
- references/index.md 5.1 KB
- references/reporting/financial-statements.md 3.9 KB
- references/reporting/taxes.md 7.5 KB
- references/sdk/bkper-api-types.md 21 KB
- references/sdk/bkper-js.md 78 KB
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 · 99 lines · 51 tokens per session scan A 89c8c91895ca
bkper-cli is a skill published in the GitHub repository bkper/bkper-cli (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,893 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…