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 wlfghdr/agentic-kb --skill kb-tracker-workflowgit clone --depth 1 https://github.com/wlfghdr/agentic-kbWrote 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/wlfghdr/agentic-kb/kb-tracker-workflow)<a href="https://agentmods.dev/skills/wlfghdr/agentic-kb/kb-tracker-workflow"><img src="https://agentmods.dev/badge/skills/wlfghdr/agentic-kb/kb-tracker-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/wlfghdr/agentic-kb/kb-tracker-workflow"><img src="https://agentmods.dev/badge/skills/wlfghdr/agentic-kb/kb-tracker-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 | $0.00052 | $0.02352 |
| Opus 5.5 | $0.00021 | $0.00941 |
| Sonnet 5.5 | $0.00010 | $0.00470 |
| Haiku 4.5 | $0.00005 | $0.00235 |
Grade A, and why
kb-tracker-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 6d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: KB Tracker Workflow
This repo uses tracker-backed KB primitives and the generic GitHub governance profile. The tracker is the canonical operational home for the primitive families declared in .kb-config/layers.yaml under primitive-storage.
This skill is the local operating manual for issues, projects, labels, PRs, and tracker-backed KB artifacts. It keeps agents aligned with the repository's GitHub rules before CI has to reject a PR.
Source-of-Truth Boundaries
- KB files own synthesis, evidence, reports, durable context, and file-backed primitives.
- Tracker items own operational state for every primitive family configured as
mode: tracker. - Hybrid primitives start in files and move to tracker ownership when they cross the configured sharing boundary.
- Pull requests own proposed repository changes and must link the issue or tracker item that explains why the change exists.
- Delivery systems outside GitHub may own execution state; link to them instead of copying their status into GitHub.
Never leave two active records pretending to own the same decision, task, feature, or roadmap item.
Required Preflight
First classify whether the requested item belongs to a KB primitive family configured in the active layer's primitive-storage. For a configured tracker-backed KB primitive, before creating or updating its tracker item:
- Read
.kb-config/layers.yaml. - Find the active layer.
- Read
connections.trackers[]andprimitive-storage. - Identify whether the requested primitive is
files,tracker, orhybrid. - Require the exact canonical operation in the selected tracker's
capabilities. - Verify authentication and suitable tracker tooling are available.
- Before any tracker duplicate search, show the structured external-read preflight: tracker sources, query/filter and time window, read-only duplicate-search intent, and the proposed mutation or local output it informs. Explicit invocation authorizes the search but does not suppress this disclosure.
- Search existing KB files and tracker items for duplicates when tools are available.
- Show the exact target and mutation and wait for explicit confirmation of that one action.
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.
- 6d ago Changed · -1 lines 04c4898dee39
- 1mo ago Changed · +9 lines c875d8afedb3
- 1mo ago First seen · 203 lines · 52 tokens per session scan A 5c69a85dbd05
kb-tracker-workflow is a skill published in the GitHub repository wlfghdr/agentic-kb (10 stars, last pushed 6d ago), licensed Apache-2.0. It adds 52 tokens to every session and 2,352 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
awesome-ai-agents-curation
Help founders prepare evidence-backed AI agent project submissions and help maintainers triage project issues and pull requests for the Awesome AI Agents list.
01-sdlc
Orchestrates a request from framing to a draft pull request, autonomous or supervised, isolating implementation, independent review, and final outcome challenge. Use when the user wants to deliver a change end to end. Not for one step.
02-user-stories
Produces or refines ordered User Stories from an Epic, Product Brief, PRD, or bounded request. Use when the user wants to slice, write, assess, order, or persist Stories. Not for Epics or implementation.
07-epic
Produces or refines an outcome-based Epic for a product backlog. Use when the user wants to frame, review, resume, or persist an Epic. Not for Product Briefs, User Stories, or implementation.
09-defect
Produces or refines a backlog Defect from an observed product mismatch. Use when the user wants to report, assess, link, order, transition, or verify a defect. Not for incident response, debugging, or implementation.