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-done)<a href="https://agentmods.dev/commands/furkantokkan/agent-foundry/task-done"><img src="https://agentmods.dev/badge/commands/furkantokkan/agent-foundry/task-done/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-done"><img src="https://agentmods.dev/badge/commands/furkantokkan/agent-foundry/task-done.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 | $0.00021 | $0.00349 |
| Opus 5.5 | $0.00008 | $0.00140 |
| Sonnet 5.5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
task-done 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 5d 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 Done
Use the task-done Codex skill for this request.
Resolve a complete ID only to production/tasks/<ID>/contract.md. Require
fresh READY_TO_CLOSE evidence, zero unresolved or blocked defect-ledger rows,
and fresh VERIFIED evidence for every known defect. The close-ready state may
come from a clean direct implementation with an empty ledger or from
task-cycle; do not require a defect cycle when no defect exists. Refuse
contradictory or stale lifecycle state. Under the shared lifecycle lock, recompute the canonical
reviewed/evidence identities without rerunning tests. Preserve the defect ledger
while updating only the managed lifecycle block, and do not ask for a second
close confirmation. Never run implementation/tests, mutate Unity, commit, or
push. A later same-scope defect enters through /task-bug <ID> "<feedback>";
its downstream cycle reopens the same task and defect record safely.
For validated orphan reconciliation, --superseded-by <NEW-ID> closes the old
planning task with Closure mode: superseded only after proving the ready
replacement links back to it and the old task has no active owner or progress.
Preserve all evidence and return STALE_TASK_RECONCILIATION_REQUIRED on any
conflict; never delete the old task.
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.
- 5d ago First seen · 31 lines · 21 tokens per session scan A 12c01c7343fb
task-done is a command published in the GitHub repository furkantokkan/agent-foundry (10 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 349 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
checkpoint
Save verification state and progress checkpoint.
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
tdd
Test-driven development with tests that actually catch breaks: red before green, name the break each test catches, and the mutation check before done.
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
validated
Record durable, git-tracked evidence that a ticket was actually validated (interactive-session twin of the governor's auto-promotion).