spek-knowledge

spek-knowledge is a skill for Claude Code, Codex from jumppad-labs/spektacular. It costs 17 tokens per session (2,039 once invoked), scanned A, original, Apache-2.0.

A skill for searching, adding to, or updating a project knowledge base, which is a stored collection of notes and conventions. It uses the project’s command-line knowledge tools for these operations.

In plain words
What is it for?
Looking up known practices, contributing new information, and updating existing knowledge-base entries.
Why use it?
It lets an agent reuse and maintain shared project knowledge instead of relying only on the current conversation or source files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Looking up known practices, contributing new information, and updating existing knowledge-base entries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jumppad-labs/spektacular/spek-knowledge
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.

Any agent
npx skills add jumppad-labs/spektacular --skill spek-knowledge
Clone the repo
git clone --depth 1 https://github.com/jumppad-labs/spektacular

Made for: Claude Code, 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 spek-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/jumppad-labs/spektacular/spek-knowledge/github.svg)](https://agentmods.dev/skills/jumppad-labs/spektacular/spek-knowledge)
Your own site
<a href="https://agentmods.dev/skills/jumppad-labs/spektacular/spek-knowledge"><img src="https://agentmods.dev/badge/skills/jumppad-labs/spektacular/spek-knowledge/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 spek-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/skills/jumppad-labs/spektacular/spek-knowledge"><img src="https://agentmods.dev/badge/skills/jumppad-labs/spektacular/spek-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,039 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 61
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 76
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Excessive Agency · line 25
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00017 $0.02039
Opus 5 $0.00009 $0.01019
Sonnet 5 $0.00003 $0.00408
Haiku 4.5 $0.00002 $0.00204

Measured 9d ago against content hash 4960cc2c348a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spek-knowledge 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 9d 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.

.bob/skills/spek-knowledge/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Version check first. Before running any other command, run go run . version check.

  • On status: "match", continue with the skill and produce no version-related output.
  • On "mismatch" or "missing", the installed Spektacular files are out of date: relay the response's action message to the user, ask them to re-run go run . init <agent>, and wait for their decision before continuing.
  • Never modify or re-install any installed files yourself — refreshing the installation is always an explicit, user-initiated re-run of init.

What this skill does

This skill orchestrates the existing go run . knowledge CRUD surface for ad-hoc read, contribute, and update operations on the project's knowledge store, without starting a spec/plan/implement flow. Unlike spek-new, spek-plan, and spek-implement, it does not drive an interactive CLI state machine — it is a static playbook. The agent recognises the user's natural-language intent, picks one of three branches (lookup / contribute / update), and calls the matching go run . knowledge command directly.

When to invoke

Invoke this skill any time the user references the knowledge base, an entry, a convention worth remembering, or asks a question that the knowledge store might already answer. Typical natural-language triggers include:

  • "What do we know about X?"
  • "Search the knowledge base for Y."
  • "Remember that Z is the case." / "Add a note about Z."
  • "Update what we have on W."
  • "Recall the convention for V."

One skill handles all three intents. Discriminate by what the user actually said — do not ask the user to pick a slash command per intent.

Intent: lookup

Triggered when the user wants to read or search existing entries. A lookup does not dump the raw hit list — it returns a single consolidated, source-cited answer with duplicates removed and the most specific source winning. The flow has a deterministic stage (exact de-dup) and a judgement stage (consolidation), kept strictly separate.

Read the full file on GitHub · 83 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. 9d ago First seen · 83 lines · 17 tokens per session scan A 4960cc2c348a

Subscribe to this mod's changes

spek-knowledge is a skill published in the GitHub repository jumppad-labs/spektacular (20 stars, last pushed 5d ago), licensed Apache-2.0. It adds 17 tokens to every session and 2,039 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.