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 agentmods add skills/kkollsga/codingest/notifynpx skills add kkollsga/codingest --skill notifygit clone --depth 1 https://github.com/kkollsga/codingestWhat 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 | $0.00058 | $0.01453 |
| Opus 5 | $0.00029 | $0.00727 |
| Sonnet 5 | $0.00012 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
notify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
notify
Deliver a message to a sibling project's inbox so its maintainer/agent picks it
up on their next read-inbox. Input: a target repo (name or path) and the
message (topic + body; compose from the conversation if not given).
The most frequent target is KGLite — codingest's upstream. When a
parity-relevant bug lives in the shared code_tree logic, or the standalone
transform needs an affordance from kglite-mcp-server / kglite::api (e.g. the
MCP build-hook), that's an upstream ask: KGLite source is read-only from this
workspace, so you notify, you don't patch.
1. Resolve the target repo path
The target lives somewhere under the Koding/ parent (category folders like
Rust/, Go/, JS/, mcp-servers/; repos sit at depth 1–2, sometimes
deeper). Search by name (case-insensitive):
KODING="${PWD%%/Koding/*}/Koding"
find "$KODING" -maxdepth 3 -type d -iname '<name>' \
-not -path '*/node_modules/*' -not -path '*/.git/*' \
-not -path '*/__pycache__/*' -not -path '*/target/*' \
-not -path '*/mcp-servers/*'
- KGLite resolves to
<KODING>/Rust/KGLite— a sibling of this repo. Its inbox is<KODING>/Rust/KGLite/inbox/unread/. Writing a note there is not a source edit, so it respects the read-only rule. mcp-servers/is one externally-managed project, not a tree of repos. Its subdirs (code_review/,open_source/, …) are not notify targets — that's why*/mcp-servers/*is excluded above. To reach anything in that ecosystem, targetmcp-serversitself → its singleinbox/unread/. Never resolve a name tomcp-servers/<subdir>/.- Exactly one match → use it.
- Several matches → prefer a git repo (has
.git/); if still ambiguous, ask the user which path (show the candidates). - No match → widen with
-maxdepth 4, then ask the user for the path. - If the caller gave an absolute path directly, skip the search and use it.
Confirm the resolved path before writing if there was any ambiguity.
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.
- yesterday First seen · 115 lines · 58 tokens per session scan A 065df8f70df6
notify is a skill published in the GitHub repository kkollsga/codingest (0 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,453 once invoked, about $0.0003 per session on Opus 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
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
github-workflow
Use GitHub workflow tools to read work status, draft reports, summarize follow-ups, and execute only approved issue mutations.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
codex-session-product-reviewer-maintainer
Use when reviewing a local Codex session, task, thread, or commit as a product manager or first-principles reviewer for product correctness, scope, behavior, validation, and whether the task solved the right user problem.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.