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.
git clone --depth 1 https://github.com/infraspecdev/tesseractWrote 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/commands/infraspecdev/tesseract/lld)<a href="https://agentmods.dev/commands/infraspecdev/tesseract/lld"><img src="https://agentmods.dev/badge/commands/infraspecdev/tesseract/lld/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/commands/infraspecdev/tesseract/lld"><img src="https://agentmods.dev/badge/commands/infraspecdev/tesseract/lld.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 | $0.00043 | $0.01449 |
| Opus 5.5 | $0.00017 | $0.00580 |
| Sonnet 5.5 | $0.00009 | $0.00290 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade A, and why
lld 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLD
Generate or update a component-scoped Low-Level Design document.
Usage
/lld [<component>] [--type backend|infra]
<component>— kebab-case component identifier (matches the filedocs/lld/<component>.md). When omitted, bare/lldscans the repo for component-shaped directories and presents undocumented candidates.--type backend|infra— selects the LLD template variant. When omitted, the type is inferred from repo markers at the component's directory path (pyproject.toml/package.json/pom.xml/go.mod→ backend;*.tf/Chart.yaml/kustomization.yaml/atmos.yaml→ infra). Ambiguous detection (both backend and infra markers in the component dir) prompts the user.
Paths
This command writes the following registry-tracked path:
| Registry key | Resolved path |
|---|---|
lld_canonical_md |
docs/lld/<component>.md |
Path A (this command) always writes to the canonical path. Path B
(/plan TRD-driven authoring, M2 plan) drafts to docs/shield/<feature>/lld-<component>.md
and /implement promotes the draft to the canonical path at milestone close
(M2 plan, step 5h).
Output Paths — MANDATORY
Find the project root by locating .shield.json. The canonical LLD path is
always <project_root>/docs/lld/<component>.md — independent of
.shield.json output_dir (which controls docs/shield/ only, not docs/lld/).
Write via the lld-docs skill's atomic-write contract: <target>.tmp → rename
to <target>. On failure, remove .tmp and surface error.
Do NOT write to docs/shield/<feature>/. Do NOT write to any other
location. Do NOT silently clobber an existing populated docs/lld/<component>.md
— see "Re-run behavior" below.
Behavior
- If
<component>is provided, use it (must match^[a-z0-9-]+$). - If
<component>is omitted, scan the project root for component-shaped directories:- top-level dirs with
pyproject.toml(Python packages) - top-level dirs with
package.json(Node packages) - top-level dirs with
pom.xmlorbuild.gradle*(JVM modules) - top-level dirs with
go.mod(Go modules) - top-level dirs with
*.tffiles (terraform modules) - dirs with
Chart.yaml(helm charts) - dirs with
kustomization.yaml(kustomize bases)
- top-level dirs with
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 · 136 lines · 43 tokens per session scan A 447b54bdede0
lld is a command published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,449 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.