Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AHappyAtlas/ai-knowledge-centernpx agentmods add skills/ahappyatlas/ai-knowledge-center/aikc-project-workflowWrote 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/ahappyatlas/ai-knowledge-center/aikc-project-workflow)<a href="https://agentmods.dev/skills/ahappyatlas/ai-knowledge-center/aikc-project-workflow"><img src="https://agentmods.dev/badge/skills/ahappyatlas/ai-knowledge-center/aikc-project-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/ahappyatlas/ai-knowledge-center/aikc-project-workflow"><img src="https://agentmods.dev/badge/skills/ahappyatlas/ai-knowledge-center/aikc-project-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 | $0.00000 | $0.00971 |
| Opus 5 | $0.00000 | $0.00485 |
| Sonnet 5 | $0.00000 | $0.00194 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
aikc-project-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 9d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIKC Project Workflow Skill
Use this skill when changing the AI Knowledge Center package itself: CLI behavior, project upgrade templates, manifest loading, dashboard metadata, gates, telemetry, or this repository's AI workflow knowledge.
Stable Project Facts
- Package name:
ai-knowledge-center. - Global CLI names:
aikcandai-knowledge-center. - Published CLI entrypoint:
dist/cli/aikc.js. - Source CLI entrypoint:
src/cli/aikc.ts. - Project upgrade logic lives in
src/cli/project-upgrader.ts. - Production dashboard and API are served by Fastify from one port, default
127.0.0.1:4318. - Development uses two processes: server on
4318and Vite UI on5177.
Change Guidance
- Prefer editing
src/and rebuilding; do not hand-editdist/unless release artifacts are explicitly required. - Keep CLI options documented in
README.mdaligned withsrc/cli/aikc.ts. - Keep scaffold templates in
src/cli/project-upgrader.tsaligned with root examples inai-knowledge/. - New-project and upgrade templates must include AIKC-maintained
ai-knowledge/core/**, compatibility entrypoints, internal AI workflow scripts underai-knowledge/scripts/**, and a mandatory final knowledge-capture decision. - Keep the ownership boundary explicit:
ai-knowledge/core/**is upgraded by AIKC; project-specific reusable knowledge belongs inai-knowledge/skills/**or project-owned references. - Core workflow templates must ask agents to package repeated operations as project scripts, project skills, MCP/server tools, or references, with local host OS and remote target OS considered separately.
- Core workflow templates must treat AI workflow loops as bounded loops with explicit input, output, validation, budget, stop condition, and human escalation.
- Core workflow templates must keep AI-facing knowledge compact and maintain human-readable companions under
ai-knowledge/human/**only when meaning changes or missing companions are backfilled. - Core workflow templates must include token-efficiency guidance for minimal context loading, log summaries, structured output, caches, operations indexes, doctor commands, and compact closeout.
- Core workflow templates must preserve AIKC project capabilities that are not project-specific: manifest contract, dashboard metadata, gates/commands, MCP, telemetry, Dagger, project discovery, API automation, safe upgrade semantics, and release discipline.
- Core workflow templates must guide agents to prefer mature open-source packages over hand-rolled implementations when they improve CLI parsing, file discovery, search, schema/API contracts, logging, config paths, watchers, process execution, or MCP/server tooling.
- Keep the dashboard initialization prompt in
src/client/App.tsxaligned withsrc/cli/project-upgrader.ts, so copied prompts, CLI upgrade, and dashboard auto-init describe the same behavior. - Avoid making
aikc --versionstart the server if adding version support; handle informational flags before importingsrc/server/index.ts. - Preserve the documented behavior that
aikc upgrade --writecreates candidates for conflicts instead of overwriting project-specific files. - Existing projects should be updateable: changed local files get
*.aikc-upgrade.mdcandidates and an AI handoff prompt, not blind overwrites. - Keep knowledge token checks sparse: trigger them for explicit token/context/routing work, first run state creation, or changes to workflow entrypoints and the compact skill index.
- For token/cache/MCP evaluation, read
ai-knowledge/core/open-source-token-tools.mdafter this skill. Prefer AIKC's built-in context-pack, repo-map, log-summary, run-bounded, token-budget-check, repo-scoped filesystem MCP, andaikc mcp --project .before adding new tools. Treat Context7 as the approved optional docs lookup; treat semantic code-search MCPs as optional repo-scoped additions only whenrepo-mapis too broad. - Package publishing uses the local environment file when needed: load
NPM_TOKENfrom.env.localinto the process environment fornpm whoamiandnpm publish, never print the token, and checkNPM_TOKEN_EXPIRES_ATbefore relying on it.
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.
- 9d ago First seen · 60 lines · 0 tokens per session scan A 38e1c430f7f4
aikc-project-workflow is a skill published in the GitHub repository AHappyAtlas/ai-knowledge-center (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 971 tokens. 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
projectatlas
Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.
codex-coding-plugin
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation, skill artifacts, host smoke tests, and fake-host tests for ProjectAtlas releases.
execute-spec-in-fork
Orchestrate one approved SPEC READY through a same-directory Codex App fork: create and name the execution task, ask it to run spec-executor, route decisions through Codex Task Messenger, validate the returned receipt, and archive a completed child. Use only when the user explicitly asks to execute an approved spec in…
breaking-down-the-work
Splits scope into a product-first work breakdown that follows the 100% rule, keeps pieces from overlapping, uses outline numbers, and gives every piece a dictionary entry. Use when an epic, feature, or new subsystem needs a clean split into deliverables, or one source of truth before folders or work begin. Do not use…
staying-on-mission
Tests the current work against a written, lasting mission anchor and forces one choice, re-anchor, escalate, or stop. Use when an agent keeps finishing tasks but the work drifts from the goal, scope creeps, the same action repeats in a loop, or standards slip one small step at a time. Do not use for a tiny edit with…
closing-stale-packets
Brings an abandoned or half-filled change packet to an honest terminal state by completing it, closing it with a recorded rationale, or deleting it. Use when ng status flags a scaffold or invalid packet, a long session left a draft behind, or work was abandoned mid-packet. Do not use for an actively in-progress…