fortify

A command router for running one of three design-improvement actions: harden, optimize, or polish.

In plain words
What is it for?
Use it when refining a design, including CSS-based interfaces or Swift files for Apple-platform apps.
Why use it?
It gives separate ways to improve a design while requiring the agent to consider constraints, make changes, evaluate them, and repeat that check twice.

Command

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.

agentmods
npx agentmods add commands/adilkalam/orca/fortify
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 878 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00083 $0.00878
Opus 5 $0.00042 $0.00439
Sonnet 5 $0.00017 $0.00176
Haiku 4.5 $0.00008 $0.00088

Measured 2d ago against content hash a799aafbc1c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fortify 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • refine — 86% identical, 49 lines differ
commands/fortify.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fortify — Design Hardening Router (individual commands)

Tweak entry for the hardening verbs. Each flag is an individual command run OUTSIDE the /impeccable pipeline — no separate validator agent, so the cognition constraint loop IS the enforcement (mandatory). Zero loop logic of its own (#POISON_PATH duplication): the loop is defined once at ~/.claude/docs/reference/cognition-constraint-loop.md. Named /fortify (not /harden) because commands never shadow existing skills; Skill("harden") is reached via /fortify --harden.

Parse flag (exactly one required)

Flag Verb / craft skill
--harden harden
--optimize optimize
--polish polish

If no flag or an unrecognized flag: print this table, ask the user to pick. Do not guess. Do not run.

Run — the in-thread cognition constraint loop

Target routing (#PATH_DECISION — one rule, not 5 copies): apply ~/.claude/docs/concepts/ios-design-contract/target-routing.md. If the TARGET ends in .swift, load Skill("ios-impeccable-hub") (instead of impeccable-hub) and use the Swift detector below; otherwise keep the CSS path unchanged.

Run the loop at ~/.claude/docs/reference/cognition-constraint-loop.md with VERB = <flag>, loading Skill("impeccable-hub") (the aesthetic; Skill("ios-impeccable-hub") for a .swift target — see routing above) + Skill("<flag>") (craft spine; felt-state framing is especially load-bearing for --harden — design for someone having a bad day):

  1. R1 BIND — cognition checkpoint emits the typed FORBIDDEN/FORWARD constraints; capture the ids.
  2. R2 WORK — edit the target in-thread under the bound ids, applying the craft + the user's critique verbatim (FR-6). Before writing styling code, read the relevant doctrine: the CSS manifesto (~/.claude/docs/concepts/llm-css-manifesto.md) for web; the loaded ios-impeccable-hub for a .swift target (per the routing rule above).
  3. EVALUATE — check every bound constraint + run the detector self-check (.swiftswiftdesigncheck detect --json <file>; else designcheck.js detect --json <file> — see the routing rule); record a cognition thought.
  4. R(n) LOOP — fix + re-evaluate until none unsatisfied. MAX N=2, then escalate. You may NOT claim done with an open constraint.

Read the full file on GitHub · 64 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. 2d ago First seen · 64 lines · 83 tokens per session scan A a799aafbc1c9

Subscribe to this mod's changes

fortify is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 878 once invoked, about $0.0004 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.