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/rossoctl/examples/wiki-discovery-clinpx skills add rossoctl/examples --skill wiki-discovery-cligit clone --depth 1 https://github.com/rossoctl/examplesWhat 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 | $0.00000 | $0.00629 |
| Opus 5 | $0.00000 | $0.00315 |
| Sonnet 5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
wiki-discovery-cli 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kwiki Discovery Agent (CLI)
Write new knowledge to the wiki memory service using the wiki_cli.py command-line tool.
Prerequisites
The wiki service must be running on http://localhost:8321. Run from the wiki_memory_tool/ directory.
Procedure
1. Check Novelty First
uv run python wiki_cli.py discover novelty {topic_id} "Page Title" "Brief summary of content"
Output: NOVEL: ... or NOT NOVEL: ... with similar pages listed.
If NOT NOVEL, do not write.
2. Get a Template (optional)
uv run python wiki_cli.py discover template # List all
uv run python wiki_cli.py discover template paper-summary # Get specific
Available templates: paper-summary, concept-overview, how-to-guide, comparison.
3. Write a Page
uv run python wiki_cli.py discover write {topic_id} {path} --content "# Title\n\nContent"
uv run python wiki_cli.py discover write {topic_id} {path} --file content.md
Options:
--message "commit message"— customize git commit message--draft— submit as draft for review instead of publishing immediately
On success, the CLI shows suggested links to related pages.
4. Submit as Draft (optional)
uv run python wiki_cli.py discover write {topic_id} {path} --draft --content "..."
Drafts are stored pending review. An admin can approve or reject them.
Authentication
GitHub Login (recommended)
uv run python wiki_cli.py --base-url https://wiki-service.example.com login
uv run python wiki_cli.py whoami
SPIFFE Headers (agent mode)
Without a cached token, the CLI uses simulated SPIFFE headers.
Options
| Flag | Default | Description |
|---|---|---|
--base-url |
http://localhost:8321 |
Service URL |
--topic |
ai |
Default topic (used for SPIFFE ID) |
--trust-domain |
rossoctl.example.com |
SPIFFE trust domain |
Example Flow
# Get template
uv run python wiki_cli.py discover template paper-summary
# Check novelty
uv run python wiki_cli.py discover novelty ai "LoRA" "Low-rank adaptation for fine-tuning"
# Write if novel
uv run python wiki_cli.py discover write ai lora.md --content "# LoRA\n\n..."
# Write as draft for review
uv run python wiki_cli.py discover write ai experimental.md --draft --file ./notes/draft.md
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 First seen · 93 lines · 0 tokens per session scan A 1267aa8372f2
wiki-discovery-cli is a skill published in the GitHub repository rossoctl/examples (11 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 629 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 2026-08-30.
Other skills, from other repositories
importing-a-codebase
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).
starting-a-new-project
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.