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 skills/tjmustard/hypergraph-coding-agent-framework/hyper-contextualizenpx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-contextualizegit clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-FrameworkWhat 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 | $0.00066 | $0.01643 |
| Opus 5 | $0.00033 | $0.00822 |
| Sonnet 5 | $0.00013 | $0.00329 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
contextualize 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 yesterday.
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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyper-Contextualize
This skill audits the installed HACF agent instruction files (CLAUDE.md, AGENTS.md,
GEMINI.md) to verify they frame HACF as a development toolchain rather than the
project subject. It also checks README.md for HACF context bleed.
Run this skill:
- After installing HACF into an existing project for the first time
- When you notice the AI treating HACF skills/schemas as the project's own features
- After
/hyper-updateif you merged agent files and the framing may have been lost
Step 1 — Pre-flight Check
Verify .agents/ exists in the current directory. If not, halt with:
ERROR: No .agents/ directory found. This is not an HACF project.
Step 2 — Scan Agent Files
Read each of the following from the project root if they exist:
CLAUDE.md, AGENTS.md, GEMINI.md, README.md
For each agent file (CLAUDE.md, AGENTS.md, GEMINI.md), check:
- Framing banner present? Look for the string
HACF as a Toolchainnear the top of the file. - Internal migration notice present? Look for any of:
deadline 2026-06-17,CI lint will enforce,docs/MIGRATION_RULES.md. - Framework Upgrade & Maintenance section present? Look for a heading with exactly that text — it describes
/hyper-updateinternals and should not appear in user project docs.
Step 3 — Report Findings
Print a structured audit report:
HACF Contextualization Audit
─────────────────────────────────────────────
✅ CLAUDE.md — Framing: PRESENT | Internal notices: NONE
⚠️ AGENTS.md — Framing: MISSING | Internal notices: FOUND (migration notice)
❌ GEMINI.md — File not found (Gemini not installed — skip)
📄 README.md — Checked (see findings below)
If all installed agent files pass all checks: output [CONTEXTUALIZED: OK] and stop.
Step 4 — Ask How to Fix
If any issues were found, use AskUserQuestion with these options:
- Replace with install templates (Recommended) — copies
.agents/install-templates/<file>over each affected file. Canonical framing, no stale notices. Project-specific customizations in the current files will be lost. - Inject framing banner only — prepends the "HACF as a Toolchain" block to each affected file without touching the rest. Preserves existing content but does NOT remove stale migration notices.
- Show diff first, decide per file — display a summary of differences between install template and current file, then ask Replace / Inject / Skip for each file individually.
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.
- yesterday First seen · 157 lines · 66 tokens per session scan A 4888261f870d
contextualize is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,643 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…