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 rdudov/task-agent --skill task-artifactsgit clone --depth 1 https://github.com/rdudov/task-agentWrote 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/rdudov/task-agent/task-artifacts)<a href="https://agentmods.dev/skills/rdudov/task-agent/task-artifacts"><img src="https://agentmods.dev/badge/skills/rdudov/task-agent/task-artifacts/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/rdudov/task-agent/task-artifacts"><img src="https://agentmods.dev/badge/skills/rdudov/task-agent/task-artifacts.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 | $0.00063 | $0.01673 |
| Opus 5.5 | $0.00025 | $0.00669 |
| Sonnet 5.5 | $0.00013 | $0.00335 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
task-artifacts 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Artifacts (durable progress)
The task directory is the source of truth, not the chat. Update artifacts during work, not only at the end.
Required files by phase
| Phase | Files | Action |
|---|---|---|
| Start | task.md, plan.md |
Status in_progress; contract in task_contract.json if gates exist |
| Research | sources.md, findings.md |
Append sources; short findings per topic |
| Implementation | plan.md |
Check off completed steps; note blockers inline |
| Verification | verification.md |
Every live smoke / contract gate — redacted, no secrets |
| Follow-up | findings-*.md |
Optional topic files (e.g. findings-api.md) |
| Delivery | deliverables/, deliverables/manifest.json |
Every explicitly requested output file, registered by basename |
| Done | task.md |
Status done; acceptance criteria [x] |
Runner-managed (when using task-runner): trace.md, status.json, progress.json — keep in sync with the table above.
verification.md (mandatory for live checks)
Create on first smoke. Structure:
# Verification: <task-id>
Date: YYYY-MM-DD
Environment: <repo>, IFT/prod, secrets redacted
## <gate_id or short name>
- Result: **OK** | **FAIL** | **GAP** (explain)
- Evidence: one-line outcome (counts, tool names, paths — no tokens)
Exact commands belong in structured evidence when a contract requires them.
This human summary records the deciding result and a concise redacted
observation. If task_contract.json defines required_live_evidence, each
required id needs a matching section with a passing Result; a heading alone,
or a later FAIL, GAP, or BLOCKED, refuses completion. Verification files
are append-only, so the last section for a repeated gate id is authoritative.
Never paste API keys, tokens, or .env values.
findings.md vs chat
After research, write:
sources.md— links, file paths, or source identifiersfindings.md— decisions, API shapes, and verification outcomes
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 · 150 lines · 63 tokens per session scan A 8a0e4cb1272e
task-artifacts is a skill published in the GitHub repository rdudov/task-agent (4 stars, last pushed 7d ago), licensed MIT. It adds 63 tokens to every session and 1,673 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…