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 manishiitg/coding-agent-loop --skill hyperframes-qualitygit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/hyperframes-quality)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/hyperframes-quality"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/hyperframes-quality/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/manishiitg/coding-agent-loop/hyperframes-quality"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/hyperframes-quality.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 | $0.00087 | $0.00637 |
| Opus 5.5 | $0.00035 | $0.00255 |
| Sonnet 5.5 | $0.00017 | $0.00127 |
| Haiku 4.5 | $0.00009 | $0.00064 |
Grade A, and why
hyperframes-quality 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HyperFrames quality gate
Review the exact source project and exact candidate render. Do not treat a successful render command as quality evidence. Read hyperframes-cli first; then read hyperframes-core, hyperframes-creative, hyperframes-animation, or hyperframes-keyframes only when their area is in scope.
Run the gate
- Validate the source. Run
hyperframes check. Resolve structural, deterministic-timeline, layout, and contrast findings before continuing. Usehyperframes inspect --jsonfor dense compositions or targeted timestamps; inspect every major text/data moment, scene transition, and the ending. - Review rendered evidence. Render a draft when no candidate render exists. Extract a contact sheet and representative frames from that rendered MP4, including opening, scene midpoints, dense text/data moments, transitions, and ending. For multi-composition projects, prefer rendered-MP4 frame extraction over snapshot-only evidence; it is the delivery truth.
- Critique craft. Compare the evidence with
BRIEF.md,STORYBOARD.md,SCRIPT.md, andframe.mdwhen present. Check:- message clarity by scene two and evidence/claim fidelity;
- safe areas, typography, contrast, hierarchy, and readable playback-speed copy;
- transitions, pacing, continuity, and whether motion explains rather than decorates;
- seek-safe timing, no stale frames, clipping, blank states, or unintended repeated/frozen frames;
- design-system adherence and an intentional opening and ending.
- Repair, then re-check. Fix the editable HyperFrames source, repeat only the affected checks, render again, and re-inspect. Use no more than two repair passes in a workflow gate. If a material issue cannot be proven fixed, return
reviseorblocked; never pass it onward.
Record a decision
Write a concise scorecard alongside the stage report. Include schema_version: 1, the exact source/archive and candidate path, inspected timestamps, checks with evidence, repair passes, final verdict (pass, revise, or blocked), and a concrete recommended action. A pass requires evidence for every applicable composition check.
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.
- 1mo ago First seen · 31 lines · 87 tokens per session scan A 058bf3b87d18
hyperframes-quality is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 87 tokens to every session and 637 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 2026-08-30.
Other skills, from other repositories
gitnexus-impact-analysis
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?".
agency-codebase-archaeologist
Multi-session, multi-tool drift detection specialist who audits codebases touched by several AI coding tools (Claude, Cursor, Copilot, Windsurf, etc.) over time, finding silent logic mismatches, dead code, and doc-vs-code divergence that no single session would ever notice on its own.
agency-minimal-change-engineer
Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.
patch-edit
Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.
code-changes
Workflow for any task that ends in code changes: issue analysis or triage, pull request review comments, features, bug fixes, refactors. Invoke at the start of such a task, before reading or writing code.
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…