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 oborchers/fractional-cto --skill symmetrygit clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/symmetry)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/symmetry"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/symmetry/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.
<a href="https://agentmods.dev/skills/oborchers/fractional-cto/symmetry"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/symmetry.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00069 | $0.03446 |
| Opus 5.5 | $0.00028 | $0.01378 |
| Sonnet 5.5 | $0.00014 | $0.00689 |
| Haiku 4.5 | $0.00007 | $0.00345 |
Grade A, and why
symmetry 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 5d 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Things Must Look Parallel
If two functions do analogous work, they must have analogous structure. Same parameter order. Same return shape. Same error handling pattern. Same naming scheme. No exceptions. No "well, this one is slightly different because..." -- stop. If the work is parallel, the code is parallel. Period.
Symmetry is not aesthetics. It is how a reader builds a mental model of your codebase. When create_user and create_product have the same shape, the reader learns the pattern once and applies it everywhere. When they differ -- different parameter order, different return type, different error wrapping -- the reader must re-learn the pattern for every module. That is a tax on every person who touches the code for the rest of its life.
The Symmetry Rule
If two things do analogous work, they must have analogous structure.
This applies at every level:
- Function signatures -- same parameter order, same types, same defaults
- Return shapes -- same envelope, same field names, same error representation
- Error handling -- same wrapping strategy, same logging, same recovery pattern
- Naming -- same verb/noun scheme, same prefixes, same suffixes
- File structure -- same sections, same ordering, same grouping
- Test structure -- same setup, same assertion style, same teardown
CRUD Symmetry
CRUD handlers are the most common symmetry violation. Every handler for a resource must have identical structure: same logging calls, same error handling, same response shape. If create logs the operation, delete logs the operation. If read wraps errors in a ServiceError, update wraps errors in a ServiceError.
GOOD -- symmetric CRUD:
class UserService:
def create_user(self, data: CreateUserInput) -> ServiceResult[User]:
logger.info("creating user", extra={"email": data.email})
try:
user = self.repo.insert(data)
return ServiceResult(data=user, error=None)
except DatabaseError as exc:
logger.error("failed to create user", extra={"error": str(exc)})
return ServiceResult(data=None, error=ServiceError.from_exception(exc))
def get_user(self, user_id: str) -> ServiceResult[User]:
logger.info("getting user", extra={"user_id": user_id})
try:
user = self.repo.find_by_id(user_id)
return ServiceResult(data=user, error=None)
except DatabaseError as exc:
logger.error("failed to get user", extra={"error": str(exc)})
return ServiceResult(data=None, error=ServiceError.from_exception(exc))
def update_user(self, user_id: str, data: UpdateUserInput) -> ServiceResult[User]:
logger.info("updating user", extra={"user_id": user_id})
try:
user = self.repo.update(user_id, data)
return ServiceResult(data=user, error=None)
except DatabaseError as exc:
logger.error("failed to update user", extra={"error": str(exc)})
return ServiceResult(data=None, error=ServiceError.from_exception(exc))
def delete_user(self, user_id: str) -> ServiceResult[None]:
logger.info("deleting user", extra={"user_id": user_id})
try:
self.repo.remove(user_id)
return ServiceResult(data=None, error=None)
except DatabaseError as exc:
logger.error("failed to delete user", extra={"error": str(exc)})
return ServiceResult(data=None, error=ServiceError.from_exception(exc))
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.
- 5d ago First seen · 346 lines · 69 tokens per session scan A 823e776f4c86
symmetry is a skill published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 69 tokens to every session and 3,446 once invoked, about $0.0003 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 2026-10-13.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…