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 Cynrath/agent-context-kit --skill ackit-workflowgit clone --depth 1 https://github.com/Cynrath/agent-context-kitWrote 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/cynrath/agent-context-kit/ackit-workflow)<a href="https://agentmods.dev/skills/cynrath/agent-context-kit/ackit-workflow"><img src="https://agentmods.dev/badge/skills/cynrath/agent-context-kit/ackit-workflow/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/cynrath/agent-context-kit/ackit-workflow"><img src="https://agentmods.dev/badge/skills/cynrath/agent-context-kit/ackit-workflow.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 | $0.00026 | $0.00722 |
| Opus 5.5 | $0.00010 | $0.00289 |
| Sonnet 5.5 | $0.00005 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
ackit-workflow 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACKit Workflow
Activate for any repository work session so tasks stay auditable.
See task lifecycle for statuses, gates, and archive rules.
Steps
- Discover work with
ackit task list/ackit task show <id>; active work lives indocs/tasks/active/(completed work lives indocs/tasks/archive/and is resolved by ID, never treated as open). If none matches, create one withackit task create "<title>" [--intent INTENT-####] [--spec <path>] [--decision <path>] [--plan <path>](never invent IDs). - Keep exactly one
[~]active checklist item; implement only that item; plan before code. - For workflow-enabled tasks, honor the declared profile:
ackit workflow set <id> --profile quick|standard|high-risk,ackit workflow show <id>,ackit workflow advance <id>,ackit workflow verify <id> --outcome pass|fail. ProvideintentRef/specRefs/decisionRefs/planRefwhen the stage requires them; referenced files must exist on disk. - Checkpoint long work:
ackit checkpoint create <id> --next-objective "<text>",ackit checkpoint show <id>,ackit checkpoint validate <id>,ackit checkpoint export <id> [--out <file>]; resume withackit task resume <id>. - Link proof, do not assert it:
ackit evidence sync <id>,ackit evidence verify <id> --criterion AC-001 --type test --ref "<proof>",ackit evidence validate <id>; independent check viaackit verification bundle <id>thenackit verification record <id> --verdict <file>/ackit verification show <id>; watch drift withackit drift check <id>(ackit drift check-activeat the pre-commit gate). - Complete only through the composed gate: evidence complete, required verdict
PASS/PASS_WITH_WARNINGSwith zero blocking findings, stage complete, no unresolvedfailattempt, no blocking drift.VERIFY failed -> completedis impossible without explicitackit task complete <id> --force(tier2 boundary). Never mark[x]without command output in Completion notes. - Archive after final evidence:
ackit task archive <id>(bulkackit task archive --completed [--dry-run]moves completed-only; pending/active/blocked never move).ackit task doctorreportsTASK-COMPLETED-IN-ACTIVEfor completed work left inactive/. - Gates before commit:
ackit doctor,ackit task doctor,ackit scan --ci; run the task's own test plan and paste pass/fail counts into Completion notes; focused Conventional Commit, then immediately continue with the next dependency-ready task.
What ships with it
1 file 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 Changed · +4 lines 81acd66561de
- 1mo ago First seen · 24 lines · 26 tokens per session scan A f894f4c6b3cf
ackit-workflow is a skill published in the GitHub repository Cynrath/agent-context-kit (14 stars, last pushed 12d ago), licensed MIT. It adds 26 tokens to every session and 722 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 2026-08-30.
Other skills, from other repositories
steadyagent-workflow
Local-first Codex workflow for planning, debugging, reviewing, refactoring, improving AGENTS.md, building skills, publishing agent harness repositories, or running complex multi-step coding tasks that need staged diagnosis, context control, verification loops, review strategy, release evidence, and…
agents-doctor
Validate AGENTS.md and related agent instruction files with the published agents-doctor CLI. Use when the user asks to check, lint, verify, explain, audit, fix, release-check, or compare AGENTS.md, CLAUDE.md, GEMINI.md, agent instruction inheritance, tool profiles, context fidelity, instruction graphs, GitHub…
adding-an-audit-check
Add a new audit check to agent-context-doctor end to end, including config, suppressions, the check catalog, tests, and docs. Use when asked to detect a new kind of problem in agent instruction files.
repository-bootstrap
Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.
repository-hygiene
Perform a read-only evidence-based audit of stale docs, agent files, scripts, generated artifacts, duplicate code, and optional tools. Use only when explicitly asked for cleanup or governance review; do not delete or refactor during the audit.
safe-change
Trace, implement, test, and independently review one bounded software change. Use for ordinary feature, bug-fix, or refactor work after the repository is bootstrapped; do not use for broad repository cleanup, production operations, or undefined rewrites.