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 skills/endogenai/dogma/conventional-commitnpx skills add EndogenAI/dogma --skill conventional-commitgit clone --depth 1 https://github.com/EndogenAI/dogmaWhat 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 | $0.00094 | $0.02134 |
| Opus 5 | $0.00047 | $0.01067 |
| Sonnet 5 | $0.00019 | $0.00427 |
| Haiku 4.5 | $0.00009 | $0.00213 |
Grade A, and why
conventional-commit 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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conventional Commit
This skill enacts the Algorithms Before Tokens axiom from MANIFESTO.md by encoding commit message conventions as a reusable procedure, eliminating per-session re-prompting overhead. Commit discipline is governed by AGENTS.md § Commit Discipline and CONTRIBUTING.md § Commit Discipline. When this skill and those documents conflict, the primary documents take precedence.
1. Format
<type>(<scope>): <description>
[optional body]
[optional footer(s)]
Rules for the first line:
- Imperative mood: "add", "fix", "update" — not "adds", "fixed", "updating"
- Lowercase throughout (type, scope, description)
- No period at the end of the description
- Maximum 72 characters for the first line
- Scope is in parentheses, not brackets
Valid: docs(guides): add session-management skill reference
Invalid: Updated the docs. / DOCS: Updates guides / docs(guides): Added session-management skill reference.
2. Types
| Type | When to use | Example for this repo |
|---|---|---|
feat |
New capability, new agent, new script | feat(agents): add executive-docs agent |
fix |
Correction to existing content or code | fix(scripts): handle missing .tmp dir in prune_scratchpad |
docs |
Documentation only — no code or script change | docs(guides): clarify encoding checkpoint format |
chore |
Tooling, scripts, templates, config — no production logic | chore(scripts): add scaffold_workplan.py for plan generation |
test |
New or updated tests | test(scripts): add coverage for validate_synthesis error cases |
refactor |
Restructuring without content or behaviour change | refactor(agents): extract session-mgmt handoff to skill |
ci |
CI configuration, workflow files, pre-commit hooks | ci: add validate_skill_files check to lint job |
perf |
Performance improvement | perf(scripts): cache URL validation results in fetch_source |
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.
- yesterday First seen · 206 lines · 94 tokens per session scan A a3268a5cfd17
conventional-commit is a skill published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 94 tokens to every session and 2,134 once invoked, about $0.0005 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 skills, from other repositories
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
auth-security
Secure authentication and authorization when credentials, sessions, roles, or permissions change.
karpathy-principles
Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
orloj-generator
Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…
api-design
Design or review REST/GraphQL APIs when endpoints or contracts change.
database-design
Design schemas and migrations when persistent data structures change.