agentmods.dev

skillport AGENTS.md

Repository guidance for Skillport, including rules for planning, indexing, fallback search, logging, documentation, and code structure. A fallback chain is a sequence of backup methods used when the preferred search method is unavailable.

In plain words
What is it for?
It guides agents building or changing task plans, category and tag handling, vector and text search, MCP communication, and shared helper code.
Why use it?
It helps keep search behaviour, configuration defaults, logs, plans, and documentation consistent across the project.

Instructions file for CodexOpenCode

409 2mo ago A scan 813 tokens original MIT
View the source file gotalab/skillport
Install

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.

agentmods
npx agentmods add instructions/gotalab/skillport/agents-md
Clone the repo
git clone --depth 1 https://github.com/gotalab/skillport

Made for: Codex, OpenCode.

Per session 813 This file is loaded in full into every session.
When invoked 813 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00813 $0.00813
Opus 5 $0.00407 $0.00407
Sonnet 5 $0.00163 $0.00163
Haiku 4.5 $0.00081 $0.00081

Measured yesterday against content hash 741d2ac2a338, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillport 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 yesterday.

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.

AGENTS.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines & Context

1. Core Principles (10-second recall)

  • PLAN.md: SSOT for「どう作るか」(how to build); keep tasks in docs/latest/PLAN.md, update continuously, snapshot at release.
  • Task tracking: Use checkbox lists (- [ ]/- [x]); include Task ID for larger work.
  • Safe defaults: Default EMBEDDING_PROVIDER=none; when enabling external providers, fail fast on missing keys.
  • Normalization: Always trim+lowercase category/tags for indexing, filtering, and search.
  • Fallback chain: Preserve vector → FTS → substring fallback; never break the chain.
  • MCP logging: stdout is JSON-RPC only; send all logs/debug to stderr.
  • Behavioral regression tests (golden traces): Not required now; add for critical flows when ready.
  • Refactoring style: Prefer function-based design with dict dispatch over class-based Strategy/ABC patterns. Keep helpers small; share common logic via helper functions, not inheritance.
  • Docs governance: See docs/AGENTS.md for layout/roles; docs/steering/OPERATING_MODEL.md for doc/release ops; docs/steering/ENGINEERING_GUIDE.md for technical policy; docs/steering/RUNBOOK.md for operational steps.

2. Project Context

Architecture

  • Brand: SkillPort
  • Packages: skillport (CLI), skillport-mcp (MCP server), skillport-core (shared lib)
  • Type: CLI + MCP Server (Model Context Protocol)
  • Stack:
    • Runtime: Python 3.10+
    • Package Manager: uv
    • MCP Lib: fastmcp
    • Database: lancedb (Vector + FTS)
    • Config: pydantic-settings

Directory Structure

  • packages/skillport-core/src/skillport/: Source code (modular monolith)
    • interfaces/cli/: Typer CLI adapter
    • interfaces/mcp/: FastMCP server adapter
    • modules/skills/: Skill management public/internal APIs
    • modules/indexing/: Index build/query logic
    • shared/: Config, types, utils, exceptions
  • docs/latest/: Living documentation (SSOT)
  • docs/releases/vX.Y.Z/: Release snapshots (frozen)
  • docs/steering/: Governance & guides
  • .skills/: Local skills storage for testing
  • verify_server.py: Verification script (Mock Client)

Read the full file on GitHub · 58 lines

Changes

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.

  1. yesterday First seen · 58 lines · 813 tokens per session scan A 741d2ac2a338

Subscribe to this mod's changes

skillport AGENTS.md is an instructions file published in the GitHub repository gotalab/skillport (409 stars, last pushed 2mo ago), licensed MIT. It adds 813 tokens to every session, about $0.0041 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.

Data and AIMemory and contextWriting and docsagent-skillsai-agentclaudecodexcontext-engineeringgithub-copilot
Related

Other instructions, from other repositories

apm tests.instructions.md

Test conventions: URL assertions must use urllib.parse, never substring.

microsoft/apm · 3,329 tokens

apm cli.instructions.md

CLI Design Guidelines for visual output, styling, and user experience standards.

microsoft/apm · 1,211 tokens

apm integrators.instructions.md

Architecture rules for file-level integrators (BaseIntegrator pattern).

microsoft/apm · 983 tokens

apm copilot-instructions.md

Instructions for microsoft/apm, covering linting (canonical contract), ci-mirror commands, local workflow, common surprises and lifecycle binding.

microsoft/apm · 827 tokens

apm architecture.instructions.md

Single canonical owner discipline: one authority per durable decision, guarded by a regression test + a static boundary check.

microsoft/apm · 2,689 tokens

apm cicd.instructions.md

CI/CD Pipeline configuration for PyInstaller binary packaging and release workflow.

microsoft/apm · 2,842 tokens