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 infraspecdev/tesseract --skill execute-stepsgit 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/skills/infraspecdev/tesseract/execute-steps)<a href="https://agentmods.dev/skills/infraspecdev/tesseract/execute-steps"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/execute-steps/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/infraspecdev/tesseract/execute-steps"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/execute-steps.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 | $0.00032 | $0.00881 |
| Opus 5.5 | $0.00013 | $0.00352 |
| Sonnet 5.5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
execute-steps 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Steps
Thin step-tracking utility for individual Shield skills. Each skill defines a fixed skeleton of mandatory steps, then drives shield/scripts/steps_store.py to register them and update status. The script writes steps.json to the exact path the session-start hook reads, so an interrupted run can be offered for resume.
This is NOT a cross-phase orchestrator. Each skill calls the script independently for its own work.
Never hand-write steps.json with the Write tool. Always go through steps_store.py — it computes the correct path and the correct schema. Hand-writing puts the file where the hook can't find it.
When to Use
- Called by a skill at startup to register its step skeleton
- Called by a skill after each step to update status
- Called by a skill to check for and resume interrupted work
When NOT to Use
- Directly by users — skills call this, not users
- As a cross-phase pipeline — each skill manages its own phase
Quick Reference
Run with uv run shield/scripts/steps_store.py <cmd>. The script resolves the path itself — pass no path.
| Lifecycle Hook | Command |
|---|---|
| Startup | read first → if it returns an incomplete doc, offer resume or fresh; then init --skill <name> --feature <slug> --steps-json '<json array>' |
| Before step | start <id> |
| After step | complete <id> [--output <path>] — or fail <id> → stop |
| All done | clear |
The --steps-json array holds the skeleton — each step is {"id": N, "action": "...", "mandatory": true}. Conditional steps add "mandatory": false; init defaults status to pending and mandatory to true. See --help for all flags.
Where steps.json lives
steps_store.py resolves it to ${SHIELD_HOME:-~/.shield}/projects/<project>/steps.json, where <project> comes from the nearest .shield.json. This is the path the session-start hook reads. You do not compute or type this path — the script does.
On resume, the session-start hook shows: Incomplete: research phase (step 2/5 — Research agents). Run the skill command to resume. The skill then runs read and asks: "Resume from step 2 or start fresh?"
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 · 61 lines · 32 tokens per session scan A 46a9dc13957e
execute-steps is a skill published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 881 once invoked, about $0.0001 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…