agentmods.dev

GPTkms: Skill for Codex

.codex/skills/kms-answer-from-wiki/SKILL.md

kms-answer-from-wiki is a skill for Codex from sc28249782/GPTkms. It costs 103 tokens per session (480 once invoked), scanned A, original, MIT.

A knowledge-retrieval guide for answering questions from a local GPTKMS knowledge base before using raw notes or general reasoning. GPTKMS stores project and cross-project information.

In plain words
What is it for?
Retrieving and reading relevant knowledge-base pages about architecture, conventions, reusable patterns, and previous findings.
Why use it?
It helps an agent find existing project decisions and conventions instead of guessing or repeating earlier investigation.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

This is sc28249782/GPTkms's own configuration. It tells Codex how to work on GPTkms itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything GPTkms configures →

not rated 0repo 3mo ago A scan 103 tokens original MIT
View source ↗ sc28249782/GPTkms
Reuse

Borrowing it

Nothing to install: this file belongs to sc28249782/GPTkms. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sc28249782/GPTkms/main/.codex/skills/kms-answer-from-wiki/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sc28249782/GPTkms

Made for: Codex.

Wrote 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.

agentmods badge for kms-answer-from-wiki

README.md
[![agentmods](https://agentmods.dev/badge/skills/sc28249782/gptkms/kms-answer-from-wiki/github.svg)](https://agentmods.dev/skills/sc28249782/gptkms/kms-answer-from-wiki)
Your own site
<a href="https://agentmods.dev/skills/sc28249782/gptkms/kms-answer-from-wiki"><img src="https://agentmods.dev/badge/skills/sc28249782/gptkms/kms-answer-from-wiki/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.

agentmods 80×15 button for kms-answer-from-wiki

Your own site · 80×15
<a href="https://agentmods.dev/skills/sc28249782/gptkms/kms-answer-from-wiki"><img src="https://agentmods.dev/badge/skills/sc28249782/gptkms/kms-answer-from-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00103 $0.00480
Opus 5.5 $0.00041 $0.00192
Sonnet 5.5 $0.00021 $0.00096
Haiku 4.5 $0.00010 $0.00048

Measured 2mo ago against content hash b341c91ab0e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kms-answer-from-wiki 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 2mo 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.

.codex/skills/kms-answer-from-wiki/SKILL.md · 40 lines

What it actually says

Kms Answer From Wiki

Use the KMS as the first retrieval layer for repo and cross-project knowledge.

Prefer compiled pages under pages/ over raw notes under raw/. Use raw notes only when the compiled pages are missing, thin, or contradicted.

Read references/workflow.md when you need the detailed retrieval sequence or answer shape.

Workflow

  1. Call kms_get_active_context if the active bases or write policies are unclear.
  2. Call kms_build_context_pack with a short query that matches the user's actual need.
  3. If the pack is empty or weak, call kms_search with a broader query.
  4. Read the most relevant page or pages with kms_read_page.
  5. Answer from the compiled pages first and cite the page paths.
  6. If the KMS looks stale or incomplete, say so clearly and only then fall back to raw notes or general reasoning.

Rules

  • Start with kms_build_context_pack unless the user already gave an exact base_id and page_path.
  • Prefer project pages over global pages when both speak to the same question.
  • Treat duplicate-title or broken-link findings as signals that the answer may need caution.
  • Keep answers compact: summary first, then the most relevant citations.
  • Do not write new memory just because the KMS was useful; writing belongs to separate maintenance workflows.

Answer shape

  • One short answer paragraph or list.
  • Mention whether the answer came from project scope, global scope, or both.
  • Include concrete citations like projects/gptkms/pages/decisions/prototype-scope.md.

When to escalate

If the KMS returns conflicting pages, run kms_find_conflicts and explain the uncertainty instead of pretending the memory is settled.

Files

What ships with it

2 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.

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. 2mo ago First seen · 40 lines · 103 tokens per session scan A b341c91ab0e1

Subscribe to this mod's changes

kms-answer-from-wiki is a skill published in the GitHub repository sc28249782/GPTkms (0 stars, last pushed 3mo ago), licensed MIT. It adds 103 tokens to every session and 480 once invoked, about $0.0004 per session on Opus 5.5. 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.

Memory and context
Related

kms-answer-from-wiki compared with skills from other repositories

kms-answer-from-wiki next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kms-answer-from-wikisc28249782/GPTkmsSkill03mo agoMITA103Codex
knowledge-ingestopenclaw/openclawSkill394kyesterdayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A74Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
memoryopensquilla/opensquillaSkill7.1k6d agoApache-2.0A44Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex