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 ddanntheman/GrantForge --skill grant-reviewgit clone --depth 1 https://github.com/ddanntheman/GrantForgeWrote 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/ddanntheman/grantforge/grant-review)<a href="https://agentmods.dev/skills/ddanntheman/grantforge/grant-review"><img src="https://agentmods.dev/badge/skills/ddanntheman/grantforge/grant-review/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/ddanntheman/grantforge/grant-review"><img src="https://agentmods.dev/badge/skills/ddanntheman/grantforge/grant-review.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 | $0.00077 | $0.00649 |
| Opus 5.5 | $0.00031 | $0.00260 |
| Sonnet 5.5 | $0.00015 | $0.00130 |
| Haiku 4.5 | $0.00008 | $0.00065 |
Grade A, and why
grant-review 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grant Review
Two independent passes, run in this order, plus a traceability deliverable. Do not soften findings; a hard review here is cheaper than a rejection.
Pass 1 — Compliance audit
Work through requirements.md mechanically. For every requirement, verify
against the actual draft files (not from memory):
- Every required narrative section exists and answers its verbatim prompt.
- Every limit respected: pages, words, characters (count them), font, margins, spacing, file naming, file format.
- Every required attachment present or explicitly tracked as pending with an owner and date.
- Every "must/shall" statement in the announcement satisfied.
- Budget totals within award range; match requirement met; budget narrative matches workbook.
- All statistics carry citations that appear in
research/evidence.md.
Any failure is a blocker. List blockers first, plainly.
Pass 2 — Mock scorer
Adopt the persona of a tired reviewer on their fourteenth application of the day, scoring strictly against the funder's published rubric (or a standard rubric — need 25 / design 30 / capacity 20 / evaluation 15 / budget 10 — if none was published).
For each scored criterion: assign points with a one-paragraph justification written as a reviewer comment, quote the weakest passage, and state the single change that would most raise the score. Score honestly against the likely field of applicants, not against effort. Then report: total score, the three highest-leverage revisions, and a judgment — "fund", "fundable with revisions", or "not competitive as written" — with the reason.
Also run the house-style humanization check across the full application: any surviving AI tells, banned phrases, or unsourced numbers get flagged as revision items.
Deliverable — Compliance matrix (final/compliance-matrix.xlsx)
A traceability table, one row per requirement: Requirement (verbatim) | Source (page/section of announcement) | Where addressed (document, section, page) | Status (met / partial / missing) | Notes. This doubles as the
user's final pre-submission checklist and, for federal grants, a defensible
record of diligence.
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 · 68 lines · 77 tokens per session scan A 7055ffa1e269
grant-review is a skill published in the GitHub repository ddanntheman/GrantForge (2 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 649 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 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-vellum
A humanities lecture: how Renaissance linear perspective reshaped early cartography — sources, argument, and evidence. Built as a decision-grade academic research deck for faculty, graduate seminar.
bar-prep-questions
Bar prep questions — MBE or essay, targeted at your weak subjects and bar jurisdiction. Tracks misses and comes back to patterns. Use when the user says "bar prep", "MBE questions", "practice essay", or "test me for the bar".
build-guide
Help a clinic supervisor author a practice-area guide that configures how student-facing skills behave — intake questions, pedagogy posture (assist / guide / teach), review gates, cross-plugin checks, and local rules. Use when a supervising attorney wants to build or revise a per-practice-area guide, tune how the…
outline-builder
Build or extend a course outline in your format, from class notes and casebook. Scaffolds — it does not write the outline for you. Use when the user says "outline [subject]", "add to my outline", "build an outline from", or points at class materials.
memo
IRAC-scaffolded case analysis memo with research gaps flagged — the scaffold, not the analysis. Rule blocks are RESEARCH NEEDED, Application is STUDENT ANALYSIS prompts, Conclusion is blank. Use when a student needs to scaffold a case analysis memo, write up their analysis, or build an IRAC memo for a case.
semester-handoff
End-of-semester case handoff memos — the mirror of /ramp. Produces per-case transition memos and a cohort summary so the departing cohort hands work to the incoming cohort cleanly. Reads deadlines, client-comms, and case history. Use when the professor or departing students need to wrap up the semester, build…