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 agentmods add skills/bartoszarendt/agenticloop/blocked-statenpx skills add bartoszarendt/agenticloop --skill blocked-stategit clone --depth 1 https://github.com/bartoszarendt/agenticloopWrote 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/bartoszarendt/agenticloop/blocked-state)<a href="https://agentmods.dev/skills/bartoszarendt/agenticloop/blocked-state"><img src="https://agentmods.dev/badge/skills/bartoszarendt/agenticloop/blocked-state.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.02291 |
| Opus 5 | $0.00045 | $0.01145 |
| Sonnet 5 | $0.00018 | $0.00458 |
| Haiku 4.5 | $0.00009 | $0.00229 |
Grade A, and why
blocked-state 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 today.
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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blocked state
The loop must fail loudly and durably, never silently. A blocked task is not a failed task; it is a paused task with enough evidence for a human or later agent to resume.
For ownership when a gate fails, follow the canonical Gate Ownership And
Dispatched Contract section in agenticloop/AGENTIC_LOOP.md: a failing gate
routes work but does not transfer another role's mutation authority.
Use backend-neutral language first:
- task record: the durable record for the work,
- GitHub projection: issue labels and comments when the backend is GitHub,
- files projection: local Markdown task fields when the backend is local files.
The default backend is files. Read .agenticloop/project.md for task_backend before
recording a blocked state. For GitHub-backed work, state markers count only when they
start a line and appear in comments authored by the loop's GitHub account. The
[[agent: ...]] trailer from [[github-attribution]] helps identify the role, but it is
cooperative text, not security.
For files-backed operations, follow agenticloop/backends/files.md for task-file shape and frontmatter
conventions.
Transient vs durable
- Transient: provider outage, rate limit, flaky network, temporary
ghfailure. Retry once or wait if the retry is cheap and safe. If it keeps failing, record a block. - Durable: credentials missing, task contradiction, merge conflict, review deadlock, missing human decision, or unavailable external dependency. Record a block immediately.
- Ambiguity: if the task record is incomplete but the maintainer can fix it, use
needs_contextinstead of blocked.
Before routing a blocked handoff, use the read-only
npx agenticloop task handoff-preflight <id> --json result. It reports the
disposition owner and one safe repair without treating activation as operator
authorization. A stale derived observation may use the explicit
task refresh-handoff-evidence <id> --plan <path> --yes path; it cannot repair a
protected task contract, human decision, review disposition, or product file.
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.
- today Changed · +42 lines a598d3b63460
- 5d ago First seen · 207 lines · 90 tokens per session scan A 318928a1c5dd
blocked-state is a skill published in the GitHub repository bartoszarendt/agenticloop (2 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 2,291 once invoked, about $0.0005 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
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
consulting-analysis
Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…
ppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.
deerflow-maintainer-orchestrator
Use when a DeerFlow maintainer needs comment-only GitHub issue or PR handling: resolve issue/PR scopes with gh, analyze issues, post or draft issue comments, perform PR review comments, review PR or issue batches, compare competing PRs that target the same issue, give fix strategy, risk classification, and validation…
systematic-literature-review
Use this skill when the user wants a systematic literature review, survey, or synthesis across multiple academic papers on a topic. Also covers annotated bibliographies and cross-paper comparisons. Searches arXiv and outputs reports in APA, IEEE, or BibTeX format. Not for single-paper tasks — use academic-paper-review…
academic-paper-review
Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation.…