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 skills add OutlineDriven/outline-driven-development --skill axiom-modegit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/skills/outlinedriven/outline-driven-development/axiom-mode)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/axiom-mode"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/axiom-mode.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00037 | $0.01146 |
| Opus 5 | $0.00018 | $0.00573 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
axiom-mode 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Axiom mode
Contract
| Field | Bound contract |
|---|---|
| Trigger | User requests axiom, axiom-mode, axiom-compact, formal-logic, or compact form. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Changes response register only. |
| Side effect | None; response style only. |
| Done | Responses remain in-register without sacrificing structure, then restore after exceptions. |
Inputs
No external input required. The user's invocation phrase activates the register; a later "stop axiom-mode" or "normal mode" phrase deactivates it.
Procedure
-
Activate the Compacted Formal-logic English register. This ASCII-only register uses shortened-English keywords for logical connectives and follows predicate-calculus and Hoare-triple conventions for structural framing. Persist the register for every subsequent response until the user signals "stop axiom-mode" or "normal mode". Done when: the register is active and persists across responses.
-
Emit only allowed characters: A-Z, a-z, 0-9, hyphens, spaces, slash, underscore, and standard sentence punctuation (period, comma, colon, semicolon, parentheses, brackets, quotes). Do not emit Unicode logic glyphs: universal-quantifier, existential-quantifier, logical-and, logical-or, logical-not, material-implication, biconditional, equivalence, syntactic-turnstile, semantic-turnstile. Done when: the response contains only allowed characters.
-
Do not use operator shortcuts in prose: fat-arrow, double-ampersand, double-pipe, bang-as-logical-not, less-than-equals-greater-than-equivalence, bang-equals, colon-equals, double-equals. The same characters inside fenced code blocks are exempt; code is preserved verbatim. Done when: prose contains no operator shortcuts (code blocks exempt).
-
Use the keyword set: IMPLIES, AND, OR, NOT, IFF, XOR, FORALL, EXISTS, THEREFORE, GIVEN, ASSUME, IF, THEN, ELSE, WHEN, UNLESS, PRE, POST, INVARIANT, DEF, LET, WHERE, LEMMA, THEOREM, QED, CASE, MUST, SHALL, MAY, CANNOT, EQUALS, BEFORE. Done when: logical connectives use the keyword set.
What ships with it
1 file 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.
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 Changed · -24 tokens per session c6252b2514ea
- 3d ago First seen · 49 lines · 61 tokens per session scan A 0e23859cadfd
axiom-mode is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,146 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
askme
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via /askme.
slicing-code-context
Use when an exact symbol, path, entrypoint, or line range can bound a focused code question or patch proposal under a fixed source budget. Not for source changes or broad repository exploration.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
autopilot
Run a hands-off plan-to-ship pipeline by chaining existing skills. Use when the user says "autopilot", "take this from plan to shipped", "run the whole pipeline", "hands-off ship it", or "do the end-to-end build".
catchup
Use when the human returns after a gap, cannot follow the project, asks what happened, or wants a visual HTML recap page. Not for onboarding: use onboard. Not for handoff: use handoff.
llm-self-loop
Use when a button click, dashboard check, or human verdict sits inside an iteration loop. Replaces it with an autonomous gate or moves non-automatable work outside the loop. Don't use for remote, credential, publish, deploy, or irreversible changes.