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 srinitude/skills --skill dtcg-tokensgit clone --depth 1 https://github.com/srinitude/skillsWrote 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/srinitude/skills/dtcg-tokens)<a href="https://agentmods.dev/skills/srinitude/skills/dtcg-tokens"><img src="https://agentmods.dev/badge/skills/srinitude/skills/dtcg-tokens/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/srinitude/skills/dtcg-tokens"><img src="https://agentmods.dev/badge/skills/srinitude/skills/dtcg-tokens.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 | $0.00027 | $0.04450 |
| Opus 5 | $0.00014 | $0.02225 |
| Sonnet 5 | $0.00005 | $0.00890 |
| Haiku 4.5 | $0.00003 | $0.00445 |
Grade A, and why
dtcg-tokens 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 2d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dtcg-tokens
Outcome
Turn inspectable multimodal source evidence into source-specific DTCG 2025.10 JSON, evidence JSON, a standalone HTML proof artifact, and a run record. Start with the full token possibility surface, narrow it with located evidence and material experiments, and accept token values only after current rendered-pixel judgment. Never invent a source, audience, product fact, brand premise, comparison corpus, or proof claim.
Motivation
A structurally valid token file can still be generic, misleading, inaccessible, mediocre, or visually poor. Deterministic Mise tasks own repeatable mechanics so strong native vision can concentrate on source interpretation, token relationships, creative experiments, human eye, brain, and touch judgment, and final visual acceptance.
Commands
| Command | Result | Owning task |
|---|---|---|
help |
Show inputs, intents, outputs, vision requirements, and claim limits. | mise run token-help |
generate <inputs> |
Produce <name>.tokens.json, <name>.evidence.json, <name>.proof.html, and <name>.run.json. |
mise run token-run -- <args> |
validate <tokens> |
Check DTCG 2025.10 structure, values, names, references, type agreement, and cycles. | mise run token-validate -- <tokens> |
prove <tokens> <evidence> [sources] |
Assemble, inspect, and read back a source-specific standalone proof. | mise run token-prove -- <args> |
Load examples/help.md, examples/generate.md, examples/validate.md, or examples/prove.md only through the matching mise run token-help, mise run token-run, mise run token-validate, or mise run token-prove operation. Load examples/failure-global-claim.md through mise run evals only for an absolute uniqueness request.
For package maintenance, load references/generation-contract.md through mise run validate; load references/resource-and-experiment-design.md and assets/improvement-contract.json through mise run improvement-policy; load references/use-case-specificity.md and assets/use-case-contract.json through mise run use-case-policy; load assets/invocation-receipt-template.json through mise run invocation-policy -- <receipt>. If Mise is unavailable, return BLOCKED; never call a private implementation file directly.
What ships with it
60 files 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.
- .github/workflows/ci.yml 423 B
- assets/creative-source-frontier.json 1.7 KB
- assets/current-date-policy.json 734 B
- assets/decision-records.json 8.9 KB
- assets/dtcg-format-2025.10.schema.json 55 KB
- assets/evidence-template.json 8.7 KB
- assets/execution-io-map.json 11 KB
- assets/execution-step-contract.json 2.0 KB
- assets/experiment-contract.json 2.1 KB
- assets/exploration-corpus/concepts.json 1.2 KB
- assets/exploration-corpus/constraints.json 972 B
- assets/exploration-corpus/manifest.json 2.0 KB
- assets/exploration-corpus/mechanisms.json 1.5 KB
- assets/exploration-corpus/negative-patterns.json 1.3 KB
- assets/exploration-corpus/operators.json 1.7 KB
- assets/exploration-corpus/primitives.json 1.5 KB
- assets/exploration-corpus/questions.json 853 B
- assets/exploration-corpus/synthesis-contract.json 1.2 KB
- assets/exploration-corpus/technology.json 747 B
- assets/exploration-corpus/themes.json 1.2 KB
- assets/exploration-strategy-catalog.json 3.8 KB
- assets/file-trigger-policy.json 632 B
- assets/google-font-policy.json 1.5 KB
- assets/improvement-contract.json 2.6 KB
- assets/invocation-receipt-template.json 349 B
- assets/judgment-review-catalog.json 29 KB
- assets/mise-primitives-catalog.json 2.0 KB
- assets/mise-primitives.json 4.0 KB
- assets/multimodal-input-catalog.json 5.1 KB
- assets/originality-analysis-contract.json 3.4 KB
- assets/perceptual-motor-invariant-catalog.json 39 KB
- assets/primitive-lifecycle.json 7.7 KB
- assets/quality-metric-catalog.json 13 KB
- assets/screen-possibility-space.json 4.7 KB
- assets/subagent-task-contract.json 1.3 KB
- assets/token-possibility-catalog.json 4.7 KB
- assets/use-case-contract.json 44 KB
- assets/vision-probe-manifest.json 2.0 KB
- assets/visual-defect-catalog.json 96 KB
- evals/cases.json 11 KB
- evals/contract.md 3.4 KB
- evals/evals.json 10 KB
- evals/files/all-types.evidence.json 548 B
- evals/files/all-types.tokens.json 2.1 KB
- evals/files/cycle.tokens.json 91 B
- evals/files/global-claim.evidence.json 845 B
- evals/files/invalid-dimension.tokens.json 64 B
- evals/files/invalid-name.tokens.json 51 B
- evals/files/missing-vision.evidence.json 710 B
- evals/files/rejected-editorial-board.svg 3.7 KB
- evals/files/rejected-visual-precedents.json 1.7 KB
- evals/files/sample-brief.txt 732 B
- evals/files/sample.evidence.json 45 KB
- evals/files/sample.tokens.json 8.8 KB
- evals/files/vision-probe-pairs.json 3.4 KB
- evals/manifest.json 426 B
- evals/rubric.md 3.2 KB
- evals/source-lineage.json 18 KB
- evals/source-mapping.json 974 B
- evals/speed-budgets.json 332 B
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.
- 2d ago Changed · +1 lines 21b05f6e3351
- 7d ago Changed · +48 lines 71fda88a4228
- 11d ago First seen · 108 lines · 27 tokens per session scan A 9242dd3007d9
dtcg-tokens is a skill published in the GitHub repository srinitude/skills (2 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 4,450 once invoked, about $0.0001 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
youtube-search
Use when the user wants to find YouTube content on any topic: searching for videos or channels, finding creators who cover a subject, discovering tutorials, talks, or expert discussions, or looking up a channel by name or handle. Also use proactively when the user wants to research a topic and YouTube is a good…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
create-openbitfun-cinematic-wallpaper-skin
Apply the cinematic animated-wallpaper style recipe to a OpenBitFun Appearance skin. Use after loading the parent create-openbitfun-skin Skill when the user provides animated character artwork and wants a host-managed video background, source-derived glass materials, image-led cards, illustrated dialogs, reproducible…
create-openbitfun-skin
Inspect the current OpenBitFun Appearance contract and author, repair, package, or validate sparse .openbitfun-appearance skins. Use when Codex needs to discover registered scenes/components/parts/states/facets, check Style IR properties or renderer tokens, initialize or inspect a package, diagnose import failures…
diagram-maker
Create standalone SVG/HTML or editable Excalidraw diagrams for concepts, architecture, processes, flows, and whiteboards.
youtube-channels
Use when a YouTube channel is the focus: pasted @handles or channel URLs, requests to browse a creator's uploads, see what a channel has posted recently, search within a channel, or resolve a handle to a channel ID. Also use when the user names a creator and wants to explore their content or monitor their uploads. Not…