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.
git clone --depth 1 https://github.com/furkantokkan/agent-foundryWrote 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/commands/furkantokkan/agent-foundry/task-cycle)<a href="https://agentmods.dev/commands/furkantokkan/agent-foundry/task-cycle"><img src="https://agentmods.dev/badge/commands/furkantokkan/agent-foundry/task-cycle/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/commands/furkantokkan/agent-foundry/task-cycle"><img src="https://agentmods.dev/badge/commands/furkantokkan/agent-foundry/task-cycle.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 | $0.00022 | $0.00421 |
| Opus 5.5 | $0.00009 | $0.00168 |
| Sonnet 5.5 | $0.00004 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
task-cycle 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.
What it actually says
Task Cycle
Use the task-cycle Codex skill for this request.
Treat the complete block below as one raw task-cycle input. Preserve the exact ID/path, evidence, references, and repository selector.
The adapter performs no lifecycle mutation, document creation, implementation,
verification, closure, commit, or push itself. Use /task-bug [<ID>] "<feedback>" as the preferred intake for a new user-observed bug; use this
command directly to resume defects already recorded for one exact task.
If the feedback also contains a distinct out-of-scope outcome, retain
same-task defects, invoke create-task once for that outcome, and—when exactly
one ready contract is returned—automatically hand both IDs to
agent-orchestration. That orchestration must conflict-check first, use
separate worktrees for disjoint writers, keep each task's role chain
sequential, and queue single-Editor work. On any ownership/path/serialized or
Editor collision with no proven owner/order, return PARALLEL BLOCKED without
creating a writer. A proven live predecessor instead produces
WAITING_FOR_OWNER/QUEUED_AFTER_OWNER; wait for its stable handoff and release,
then resume automatically without another operator command.
The skill must check the canonical ledger, linked record, fingerprint, and
revision before reporting reuse/reopen; suspected causes remain hypotheses
until reproduction evidence confirms them.
After its internal implementer/verifier handoff, the parent cycle must resume,
refresh reviewed/evidence identities, transition every defect from verified
evidence, and record either READY_TO_CLOSE with task-done <ID> or one exact
blocker. It must not forward a child's next command or ask for task-cycle again.
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 Changed efc5d910284a
- 5d ago First seen · 38 lines · 22 tokens per session scan A acfad8f65382
task-cycle is a command published in the GitHub repository furkantokkan/agent-foundry (10 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 421 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 2026-09-25.
Other commands, from other repositories
speckit.companion.doctor
Report on a spec's run health — unfinished steps, unjournaled tasks, step bleed, drift you can judge, a step that closed having verified nothing, a step that closed without the file it promised, and why completion did not land (read-only, retroactive, never halts).
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
debug
Systematic debugging with hypotheses and evidence gathering.
debug
Structured debugging with parallel investigation agents.
validated
Record durable, git-tracked evidence that a ticket was actually validated (interactive-session twin of the governor's auto-promotion).