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 modiqo/skillspec --skill durable-executorgit clone --depth 1 https://github.com/modiqo/skillspecWrote 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/modiqo/skillspec/durable-executor)<a href="https://agentmods.dev/skills/modiqo/skillspec/durable-executor"><img src="https://agentmods.dev/badge/skills/modiqo/skillspec/durable-executor/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/modiqo/skillspec/durable-executor"><img src="https://agentmods.dev/badge/skills/modiqo/skillspec/durable-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00175 | $0.03719 |
| Opus 5.5 | $0.00070 | $0.01488 |
| Sonnet 5.5 | $0.00035 | $0.00744 |
| Haiku 4.5 | $0.00017 | $0.00372 |
Grade A, and why
durable-executor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
durable executor
Universal durable-work meta-router and first-hop execution substrate for any tool-backed CLI/API/shell/browser/provider/local-process/artifact work that should be traced, aligned, gated, or reusable.
Entry Gate
- Before any task action, run
skillspec plan ./skill.spec.yml --input='<user task>' --trace-dir "${PWD}/.skillspec/traces", preserve the printedrun_dir, then runskillspec act ./skill.spec.yml --input='<user task>' --run <run_dir> --phase <phase-id>, and read the ordered phase plan plus current-route action checklist. - Until that plan and checklist are read, the only allowed actions are loading this
SKILL.md, loading the colocatedskill.spec.yml, and running SkillSpec navigation or decision commands for this spec. - The selected route and matched rules in the checklist override lower-level skill defaults. If a tool is forbidden, stop and report that the SkillSpec blocks it.
- After each phase action, record structured progress in
<run_dir>/execution.jsonland runskillspec progress show ./skill.spec.yml --run <run_dir>before moving to the next phase. - This SkillSpec supersedes overlapping lower-level skill instructions: browser:browser.
- Forbidden before the decision: raw_repo_search, direct_file_read, direct_cli_without_rote_exec, direct_shell_command_without_rote_exec, direct_harness_cli_call_without_rote_exec, browser_browser_skill, node_repl.
This skill is a thin loader for the colocated skill.spec.yml. The spec is the source of truth for routes, rules, dependencies, imports, resources, recipes, tests, and trace requirements. Do not treat the spec as background prose; treat it as the execution contract for this task.
Runtime Contract
- Load
./skill.spec.ymlfrom this skill folder before taking task actions. - When the
skillspecCLI is available and the spec shape is unfamiliar, runskillspec sensemake ./skill.spec.yml --view indexto learn the section roles, counts, query handles, and navigation grammar without dumping the full YAML. - Then create the ordered phase plan and current-route action checklist:
What ships with it
2 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.
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 · 148 lines · 175 tokens per session scan A c6e9c90b1b10
durable-executor is a skill published in the GitHub repository modiqo/skillspec (707 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 175 tokens to every session and 3,719 once invoked, about $0.0007 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
uig
Build a User Input Grid (UIG) for an AI product or feature, evaluate existing eval datasets against it, and propose new inputs to fill coverage gaps. Use this skill whenever someone asks to design an eval framework, audit a test set, build a "user input grid", "synthetic query matrix" or "SQM", improve dataset…
eval-code
Write deterministic, code-based evaluator functions for an AI product. Use this skill whenever you need to write evaluators that check structural properties of AI outputs (format, count, presence, schema compliance) without calling another LLM. Also use when auditing existing code-based evaluators for brittleness…
eval-llm-judge
Write LLM-as-judge evaluator prompts for AI products. Use this skill whenever you need to evaluate semantic properties of AI outputs that cannot be checked programmatically — output quality, tone, factual accuracy, edge case handling, reference alignment. Also use when auditing existing judge prompts for bias…
llm-align
Analyze alignment between LLM judge scores and human labels in an eval dataset. Use this skill whenever someone wants to evaluate how well an LLM judge agrees with human reviewers, calculate TPR/TNR, investigate disagreements, or improve a scorer prompt. Trigger on phrases like: "calculate TPR/TNR", "judge alignment"…
ticket-to-eval
Strip PII from a customer support ticket or eval trace and convert it into eval dataset rows. Produces two outputs: a regression dataset row (close to the original input, tagged with failuremode) and a generalized dataset row (abstracted for broader coverage). Works with local CSV files or any eval platform. Use this…
eval-rubric
Write or update the eval rubric for an AI agent or AI feature: the pass/fail criteria that define good behavior, in four groups (outcome, trajectory, governance, experience), plus the release thresholds that belong in the PRD. Use this skill whenever someone asks to "write an eval rubric", "define what good looks…