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 instructions/nbpadilha/nbp-skillforge/agents-mdgit clone --depth 1 https://github.com/nbpadilha/nbp-skillforgeWrote 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/instructions/nbpadilha/nbp-skillforge/agents-md)<a href="https://agentmods.dev/instructions/nbpadilha/nbp-skillforge/agents-md"><img src="https://agentmods.dev/badge/instructions/nbpadilha/nbp-skillforge/agents-md.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 | $0.00524 | $0.00524 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
nbp-skillforge AGENTS.md 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 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.
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.
What it actually says
AGENTS.md
Guidance for AI agents (and humans) working in this repo. Public and intentionally short.
What this is
nbp-skillforge composes portable agent skills (SKILL.md / slash-command files) from reusable
bricks, with a drift-gate. A recipe points to bricks; forge build assembles the
final self-contained file; forge check fails if any generated file drifted from its recipe.
The one rule that matters
Never hand-edit generated output. Files under the configured out/ directory carry a
GENERATED banner — they are build artifacts. To change one, edit the recipe
(recipes/<name>.md) or the brick (bricks/<path>.md) it includes, then run forge build.
Composition lives in the recipe; bricks do not include other bricks (enforced at build) — except
inside a fenced code block (``` / ~~~), where an include directive is never expanded or
enforced, so a brick can safely document the include syntax as a fenced example.
Before you finish a change
node --testis green (zero-depnode:testsuite).node bin/cli.mjs check --root examplesreports in sync (the drift-gate; also runs in CI).- Docs updated in the same change:
README.md,SPEC.md,CHANGELOG.mdwhen behavior changes.
Conventions
- Zero runtime dependencies. Adding one needs a strong, explicit reason.
- Node ≥ 18, ESM. Source in
src/(engine + lifecycle + hooks), CLI inbin/cli.mjs. - Output is vendor-neutral — no proprietary pointer syntax leaks into generated files.
- Destructive operations are soft by default (recoverable in
_archive/). - Conventional Commits:
feat/fix/docs/refactor/test/chore.
See CONTRIBUTING.md for setup details and SPEC.md for the format.
To adopt nbp-skillforge in your project autonomously, hand an agent AGENTS-SETUP.md
— an end-to-end setup runbook with execution gates.
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 · 33 lines · 524 tokens per session scan A bff12af9d6e6
nbp-skillforge AGENTS.md is an instructions file published in the GitHub repository nbpadilha/nbp-skillforge (8 stars, last pushed 1mo ago), licensed MIT. It adds 524 tokens to every session, about $0.0026 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 instructions, from other repositories
kubb AGENTS.md
AGENTS.md instructions for kubb-labs/kubb, covering agents.md, high-level architecture, project structure and commands, repository setup and plugin ecosystem.
codex-autoresearch AGENTS.md
Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.
kessoku AGENTS.md
AGENTS.md instructions for mazrean/kessoku, covering repository guidelines — kessoku, project structure, common commands, build and test.
llm-wiki AGENTS.md
Instructions for BogdanovychA/llm-wiki, covering інструкції для агентів: хранитель llm wiki, 1. структура каталогів, 2. загальні конвенції, 3. шаблони сторінок та стандарти форматування and назви файлів.
Polaris AGENTS.md
AGENTS.md instructions for sponge-b0b/Polaris, covering agents.md, purpose and authority, domain vocabulary, coding conduct and secrets.
arandu CLAUDE.md
Instructions for vdittgen/arandu, covering arandu, architecture, top-level packages, commands and coding standards.