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/task-record-contractnpx skills add bartoszarendt/agenticloop --skill task-record-contractgit clone --depth 1 https://github.com/bartoszarendt/agenticloopWhat 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 | $0.00065 | $0.07424 |
| Opus 5 | $0.00032 | $0.03712 |
| Sonnet 5 | $0.00013 | $0.01485 |
| Haiku 4.5 | $0.00006 | $0.00742 |
Grade A, and why
task-record-contract 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 — 620 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task record contract
A task record is the durable contract for one implementation task. The engineer must be able to work from the task record without guessing.
If the current role is orchestrator, route task-record creation or refinement through [[role-delegation]] instead of writing the task record directly.
Task records are stored in the configured backend:
- Files projection: one Markdown file at
.agenticloop/tasks/<TASK-ID>.md. Seeagenticloop/backends/files.md. - GitHub projection: one GitHub issue per task when the project explicitly uses
task_backend: github. Seeagenticloop/backends/github.md.
Event Logging
Event logging is optional and off by default. When enabled, follow
[[event-logging]]: emit task.created for a new record and task.updated after
material scope, criteria, check, or backend-linkage changes. Use the task id and
a concise gate fact; never copy the task body or chat into the log.
Required sections
Use agenticloop/memory/task-record.md as the canonical task-record shape.
It defines the ordered required sections and the optional Proof Pressure,
Concurrency Plan, Parallel Safety, Grouping, Source Reference,
Applicable Project Skills, and Outcome sections. New records also include
the ## Verification Attempts section with the canonical empty state from
[[verification-evidence]]. Historical records without that optional learning
section remain readable.
The ## Outcome section is optional for routine clean tasks, maintainer-filled
at closeout. It becomes conditionally required when any of these happened:
review_rounds > 1, failed or triaged checks, blocked/needs_context state, scope
drift, stale evidence, human intervention, predicted medium/high context
overflow risk, context pressure encountered, or follow-ups. It never replaces
acceptance criteria or proof pressure.
Proof pressure
Use optional ## Proof Pressure when long-running or ambiguous work could pass
locally while missing the owner's outcome. Every field must be concrete:
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 First seen · 620 lines · 65 tokens per session scan A d860f9453b7e
task-record-contract is a skill published in the GitHub repository bartoszarendt/agenticloop (2 stars, last pushed 12d ago), licensed MIT. It adds 65 tokens to every session and 7,424 once invoked, about $0.0003 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.…