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 ssmurfgg04-gif/context-m --skill project-briefgit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/project-brief)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/project-brief"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/project-brief/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/ssmurfgg04-gif/context-m/project-brief"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/project-brief.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 | $0.00055 | $0.00844 |
| Opus 5 | $0.00028 | $0.00422 |
| Sonnet 5 | $0.00011 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
project-brief 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 8d 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.
This is a copy
100% identical to project-brief — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Brief Template
Use this template for weekly / periodic digests that should feel like a hand-assembled reporter's notebook — issue-numbered, taped, clipped, ruled, with a clear physical metaphor.
Use When
- The artifact is a recurring digest (周报 / VOL.NN / Issue N) with multiple grouped entries.
- Sections include: new features, optimizations, bug fixes, links, notes — i.e. a changelog-shaped narrative.
- The voice is product-team or editorial-team-internal, not corporate.
- The deliverable will be exported / shared as a high-res image or PDF, not just a scrolling page.
Avoid When
- The content is a one-off announcement (use a social card or blog-post).
- The audience expects a corporate formal report — this is intentionally crafty and warm.
- The user wants a presentation / deck (use
ppt/). - The content is a marketing landing — wrong carrier entirely.
Required Reading
Read this SKILL.md first. Do not read 清言周报-VOL18-notebook.html by default.
Read the pattern only when you need concrete geometry — spiral hole spacing, tape angle and deckle, binder-clip placement, receipt-grid pattern, the 31px ruled baseline. Extract patterns; do not copy placeholder issue numbers, dates, feature names, or class names wholesale.
Design Strategy
Lock the issue's spine before placing decoration:
- Masthead — logo + date strip + 1-paragraph intro.
- Issue mark — cobalt tape with VOL.NN + binder clip.
- Table of contents — three-column grid pointing to numbered sections.
- Sections — each with a kicker (uppercase Spanish / English label) + Chinese title + indexed entries.
- One "physical" highlight block — receipt for optimizations, taped Polaroid for a feature, mint folder tab for an announcement.
- Closing lockup + colophon — QR / ticket / page-number metadata.
Each issue should follow the same spine — that's how a weekly builds identity over time.
Layout Bias
Prefer:
- mixed serif (FlyFlowerSong / Noto Serif SC) + sans (Noto Sans SC) + mono (JetBrains Mono) — each carries a role
- ruled baseline grid for body copy; entries align to it
- dashed dividers between entries, not solid rules
- one or two "physical" elements per page (tape / clip / receipt / folder tab) — not all of them at once
- index numbers (01 / 02 / 03) on entries; uppercase Latin kickers above CJK section titles
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 75 lines · 55 tokens per session scan A 4e019b45ac36
project-brief is a skill published in the GitHub repository ssmurfgg04-gif/context-m (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 844 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to project-brief, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
prospect
Run a structured pre-mortem on a plan or approach BEFORE execution. Per-step risk enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, plan-formation diagnosis, action verdicts (PROCEED/SHRINK/SPLIT/DEFER/KILL)…
pptx
A guide for turning a paper, outline, or structured text into a PowerPoint presentation. It covers an 8–12-slide structure, concise slide points, and generation of a .pptx file.
pdf-reader
Extract text from PDF files. Use when reading, parsing, or analyzing PDFs.
ov-add-paper
Load when the user asks to add, import, compile, or ingest a research paper/PDF into OpenViking, especially when they mention ov-add-paper, ARA, claims, evidence, figures, tables, or paper-to-OV knowledge resources.
ocr-document
Extract text from PDFs, images, and scanned documents. Uses pymupdf (local) or optional cloud OCR APIs.
liteparse
Parse documents into LLM-ready content entirely on the local machine — PDF / DOCX / XLSX / PPTX / images → Markdown, structured JSON (with bounding boxes), or page screenshots, via the lit CLI. No cloud, no LLM, works offline. Use whenever the user attaches or points to a document that must be read before reasoning…