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.
git clone --depth 1 https://github.com/Abhinavbwj/AEC-ScholarWrote 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/abhinavbwj/aec-scholar/thesis)<a href="https://agentmods.dev/commands/abhinavbwj/aec-scholar/thesis"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/thesis/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/commands/abhinavbwj/aec-scholar/thesis"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/thesis.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 | $0.00018 | $0.00406 |
| Opus 5.5 | $0.00007 | $0.00162 |
| Sonnet 5.5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
thesis 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 1mo 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.
What it actually says
Help with the thesis/dissertation: $ARGUMENTS
Use the research-strategist and academic-writer agents and the thesis-dissertation skill (plus
research-methods, academic-writing).
Determine what the user needs and respond accordingly:
-
Format & architecture. If structuring: recommend monograph vs compilation ("stapled"/publication- based) — note this is institution-specific and tell them to confirm regulations. Then propose a chapter architecture. For a compilation, design the paper arc (e.g. review → framework/method → empirical validation → application) and the all-important synthesis ("kappa") chapter that makes the papers one contribution.
-
The golden thread. Help articulate one central aim and a small set of RQs that every chapter maps to, plus a consistent contribution statement for intro/synthesis/conclusion.
-
Per-chapter guidance. For the chapter the user is working on, apply its specific job (intro gap move; synthesis integration; methodology; results; discussion; conclusion).
-
Planning. Offer a back-planned timeline with milestones and per-paper status tracking (hand to
/aec-scholar:research-plan), building slack for AEC fieldwork/data-access delays. -
Coherence & integrity check. Flag drift in RQs/terminology, missing synthesis, over-claimed unified contribution, and authorship/copyright issues for republished papers (CRediT — see
/aec-scholar:coauthor-credit).
Offer to proceed to viva preparation (/aec-scholar:viva) when the draft is mature.
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.
- 1mo ago First seen · 34 lines · 18 tokens per session scan A 8257190d853e
thesis is a command published in the GitHub repository Abhinavbwj/AEC-Scholar (21 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 406 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
client-education
Produce patient education handouts on specific dietary topics, conditions, or lifestyle modifications.
derive
Save a clean reference derivation of a target equation or theorem to derivations/. Draws from course materials (textbook, lecture notes) rather than testing the user.
openehr-explain
One-stop router that explains or looks up any openEHR thing — auto-detects an archetype, a template, an RM/AM/BASE type, an RM structural concept, an ADL idiom, an AQL query or keyword, or a terminology code (replaces /archetype-explain, /template-explain, /type-spec, /rm-structure, /adl-idiom, /terminology).
gpd:explain
Explain a physics concept rigorously in the context of the active project or a standalone question with an explicit topic.
talk
Turn a paper (or several) into an academic talk — outline, slides, speaker notes, backups, rehearsal plan.
paper-lean
Drive a Lean / Mathlib formalization session using the paper-lean skill.