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/junsw/feature-track/feature-trackingnpx skills add JunsW/feature-track --skill feature-trackinggit clone --depth 1 https://github.com/JunsW/feature-trackWhat 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 | $0.00049 | $0.00314 |
| Opus 5 | $0.00024 | $0.00157 |
| Sonnet 5 | $0.00010 | $0.00063 |
| Haiku 4.5 | $0.00005 | $0.00031 |
Grade A, and why
feature-tracking 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 3d 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.
What it actually says
Feature Tracking
Use Feature Track as the current operational memory for feature work. The neutral spec is the source of truth; this Claude Code plugin is an adapter.
Read references/spec.md before changing feature docs.
Default Workflow
Before feature work:
- Read
docs/features/README.mdif it exists. - Identify the feature id from the request, code module, route, domain name, or existing docs.
- Read
docs/features/<feature-id>/README.mdif it exists. - If no track exists, create one and add it to the index.
During work, update the feature track when behavior, decisions, endpoints, data models, dependencies, rollout constraints, tests, or source-of-truth links change.
Before completion:
- Update the feature README for the actual outcome.
- Update
docs/features/README.mdif status, source-of-truth links, dates, or notes changed. - Run validation when available:
python3 cli/feature_track.py validate --root .
If the project does not include this CLI, use scripts/validate_feature_tracks.py from this skill.
Invoke this plugin skill in Claude Code with:
/feature-track:feature-tracking
What ships with it
4 files 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.
- 3d ago First seen · 40 lines · 49 tokens per session scan A f7b8de7248da
feature-tracking is a skill published in the GitHub repository JunsW/feature-track (107 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 314 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
agent-context-bridge
Continue CC Switch-managed Claude Code, Codex, Gemini CLI, opencode, Cursor, and Aider sessions through Agent Context Bridge handoff packets.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
digital-health-clinical-asr-finetune
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).