fortify

fortify is a command for coding agents from fcakyon/phd-skills. It costs 20 tokens per session (504 once invoked), scanned A, original, MIT.

A paper-review preparation workflow that reads LaTeX papers and experiment results, then ranks ablation studies and lists likely reviewer questions. An ablation study changes one part of an experiment to show which parts matter.

In plain words
What is it for?
Use it to choose the strongest ablations for the main paper or supplementary material and prepare answers to likely peer-review questions.
Why use it?
It helps identify which experiments best support the paper's claims and which concerns reviewers may raise before submission.

Command

Part of the phd-skills plugin — 12 skills, 6 commands, 2 agents, 4 hooks shipped together

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/fcakyon/phd-skills/fortify
Clone the repo
git clone --depth 1 https://github.com/fcakyon/phd-skills

Or install phd-skills, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 2 agents, 4 hooks.

Wrote 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.

agentmods badge for fortify

README.md
[![agentmods](https://agentmods.dev/badge/commands/fcakyon/phd-skills/fortify.svg)](https://agentmods.dev/commands/fcakyon/phd-skills/fortify)
Your own site
<a href="https://agentmods.dev/commands/fcakyon/phd-skills/fortify"><img src="https://agentmods.dev/badge/commands/fcakyon/phd-skills/fortify.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 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 $0.00020 $0.00504
Opus 5 $0.00010 $0.00252
Sonnet 5 $0.00004 $0.00101
Haiku 4.5 $0.00002 $0.00050

Measured 4d ago against content hash 80dedbab452c, 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 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.

plugin/commands/fortify.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper Fortification

You are helping strengthen a paper before submission by selecting the best ablations and preparing for reviewer questions.

Step 1: Read the Paper

  • Find and read all .tex files
  • Identify the claims made in the paper (especially in contributions and experiments)
  • Note the evaluation metrics and baselines used

Step 2: Find Experiment Results

  • Search for result files: JSON, CSV, wandb logs, checkpoint directories
  • Look for training configs that define ablation variants
  • Identify all available experimental runs and their outcomes

Step 3: Rank Ablations

For each available ablation or experiment:

Run Factor Changed Primary Metric Delta Narrative Strength Include?

Ranking criteria:

  1. Impact magnitude: largest metric improvement = most convincing
  2. Narrative strength: directly supports a specific paper claim
  3. Uniqueness: shows something no other ablation shows
  4. Anticipated questions: preemptively answers likely reviewer concerns

Recommend: main paper (top 3-5) vs supplementary (rest).

Step 4: Generate Reviewer Questions

Consider the venue: $ARGUMENTS (if provided, adjust expectations accordingly).

Generate the top 10 most likely reviewer questions:

1. [Question]
   Why they'd ask: [motivation]
   Answerable now: [Yes — point to data / No — needs new experiment]
   Draft response: [2-3 sentences if answerable]

Step 5: Identify Weaknesses

List specific weaknesses a reviewer might flag:

  • Missing baselines
  • Claims not fully supported by evidence
  • Scalability or generalization concerns
  • Missing statistical significance

Step 6: Output

## Fortification Report

### Recommended Ablation Subset
[Table with justification for each]

### Top 10 Anticipated Questions
[Numbered list with draft responses]

### Weaknesses to Address
[Prioritized list with suggested text edits]

### Suggested Edits
[Specific paragraph-level improvements]

Read the full file on GitHub · 78 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. 4d ago First seen · 78 lines · 20 tokens per session scan A 80dedbab452c

Subscribe to this mod's changes

fortify is a command published in the GitHub repository fcakyon/phd-skills (382 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 504 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.