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 commands/kaddo-kdd/kaddo/creategit clone --depth 1 https://github.com/Kaddo-kdd/kaddoWrote 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/commands/kaddo-kdd/kaddo/create)<a href="https://agentmods.dev/commands/kaddo-kdd/kaddo/create"><img src="https://agentmods.dev/badge/commands/kaddo-kdd/kaddo/create.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 | $0.00013 | $0.01951 |
| Opus 5 | $0.00006 | $0.00975 |
| Sonnet 5 | $0.00003 | $0.00390 |
| Haiku 4.5 | $0.00001 | $0.00195 |
Grade A, and why
create 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.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kaddo create feature # K2: delivers a user-facing capability
kaddo create bugfix # K2: fixes a known defect
kaddo create hotfix # K1: urgent fix on a released version
kaddo create spike # K3: exploratory / reduce uncertainty
kaddo create chore # K1: maintenance, tooling, config, infra
Work Item types
| Type | Use it for | Examples |
|---|---|---|
feature |
A user-facing capability | Create task · List tasks |
bugfix |
A known defect | Filter returns wrong results |
hotfix |
Urgent fix on a released version | Production crash · auth outage |
spike |
Exploration to reduce uncertainty | Evaluate SQLite vs PostgreSQL |
chore |
Technical/maintenance work that enables the project but adds no direct user capability | Initialize TypeScript · Configure Vitest · Setup CI · Update dependencies |
A Work Item is a chore when it does not add a capability, fix a defect, handle an emergency
or perform research — but is needed for maintenance, configuration, tooling, infrastructure or
developer experience. Classifying such work as feature distorts the meaning of Feature.
Aliases (resolve to chore automatically, from the CLI or a roadmap candidate):
setup, maintenance, tooling, infrastructure, infra, refactor, config.
New Work Items are created in knowledge/delivery/work-items/draft/ with status: draft.
Move them to ready when dependencies, scope and acceptance criteria are clear.
Optional modules add more types (adr, rfc, incident, migration, legacy,
contract, capability, guard-rule, agent, skill). See
Modules.
Create from a roadmap candidate
Once the roadmap-agent has produced knowledge/delivery/roadmap.md, you can turn a candidate work
item into a real Work Item without retyping its context:
kaddo create --from roadmap
# or pre-pick a type as default:
kaddo create feature --from roadmap
Kaddo reads knowledge/delivery/roadmap.md, lets you select a candidate (WI-CANDIDATE-001, …),
and prefills the Work Item from the roadmap: title, type, suggested Knowledge Level, expected
value, notes, related capabilities/impact/risk/dependencies, and the parent initiative. It
asks only for the required fields the candidate does not already provide.
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 · 232 lines · 13 tokens per session scan A bc5719a5e64d
create is a command published in the GitHub repository Kaddo-kdd/kaddo (47 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 1,951 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.