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/codeinfinity1/stram/task-trackingnpx skills add CodeInfinity1/Stram --skill task-trackinggit clone --depth 1 https://github.com/CodeInfinity1/StramWhat 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 | $0.00050 | $0.00668 |
| Opus 5 | $0.00025 | $0.00334 |
| Sonnet 5 | $0.00010 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
task-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 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Tracking
Purpose
Maintain a concrete working ledger of tasks and obligations using Stram's commitment, cognition, memory, and activity tools. This skill adapts external reference task tracker patterns into local-first, evidence-backed tracking.
When To Use
Use when the user asks to track work, update task status, review blockers, list follow-ups, inspect pending commitments, or continue an existing task across sessions.
Inputs And Evidence
- Current
cognitive_state. - Commitment records from
cognitive_commitment_status. - Recent run notes, memory summaries, and activity records.
- Tool outputs from the task being tracked.
- User-provided status updates.
Tool Map
cognitive_commitment_statuscognitive_commitment_recordcognitive_commitment_updatecognitive_commitment_reviewcognitive_statememory_writememory_searchactivity_search
Workflow
- Identify whether the user is asking to inspect, create, update, resolve, or summarize tasks.
- Gather current commitments and active goals before writing anything new.
- For each task, preserve title, status, owner, evidence, next action, blocker, and due/wakeup info when available.
- Update exact commitment IDs when they exist; create new records only for genuinely new obligations.
- Keep "waiting on user", "waiting on external system", and "ready to continue" distinct.
- End with a concise task board and the most useful next action.
Safety And Boundaries
- Do not mark work complete unless current evidence proves completion.
- Do not fabricate due dates or owners.
- Do not overwrite unrelated commitments because names look similar.
Safety And Approval
- Updating commitments is durable state; use exact IDs where possible and summarize evidence for each change.
- Do not close, delete, or supersede tasks unless the user requests it or current evidence proves resolution.
- Do not invent due dates, owners, urgency, or external dependencies.
- High-risk next actions remain approval-gated even when they appear on the task board.
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 · 80 lines · 50 tokens per session scan A b16c281a3ee6
task-tracking is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 50 tokens to every session and 668 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.