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 commands/fcakyon/phd-skills/fortifygit clone --depth 1 https://github.com/fcakyon/phd-skillsWrote 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/commands/fcakyon/phd-skills/fortify)<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>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 | $0.00020 | $0.00504 |
| Opus 5 | $0.00010 | $0.00252 |
| Sonnet 5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00050 |
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.
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:
- Impact magnitude: largest metric improvement = most convincing
- Narrative strength: directly supports a specific paper claim
- Uniqueness: shows something no other ablation shows
- 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]
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.
- 4d ago First seen · 78 lines · 20 tokens per session scan A 80dedbab452c
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.
Other commands, from other repositories
brainstorm
Generate 10 ranked research ideas from a topic area using structured heuristic lenses.
idea
Screen a research idea with scoring and novelty check.
lit-review
Write a structured literature review on a topic with Corbis-backed searches and BibTeX citations.
verify-citations
Verify all citations against bibliography.
lit-landscape
Generate figures visualizing literature trends, citation patterns, and research gaps.
lit-search
Search the literature and build a positioning memo.