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 tokenbender/agent-guides --skill workloggit clone --depth 1 https://github.com/tokenbender/agent-guidesWrote 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/tokenbender/agent-guides/worklog)<a href="https://agentmods.dev/skills/tokenbender/agent-guides/worklog"><img src="https://agentmods.dev/badge/skills/tokenbender/agent-guides/worklog/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/tokenbender/agent-guides/worklog"><img src="https://agentmods.dev/badge/skills/tokenbender/agent-guides/worklog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 100 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00105 | $0.01334 |
| Opus 5.5 | $0.00042 | $0.00534 |
| Sonnet 5.5 | $0.00021 | $0.00267 |
| Haiku 4.5 | $0.00011 | $0.00133 |
Grade A, and why
worklog 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 1mo 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worklog
Use GitHub issues as the durable source of truth for a body of work. Keep a master issue for the overall effort, a separate child issue for each bug, feature, experiment, or change, atomic commits for each logical unit, and issue comments as the running engineering ledger.
Core Contract
- Treat the master issue as the project ledger: scope, child issue index, current status, unresolved decisions, and final rollup.
- Treat child issues as executable work units: one bug, feature, experiment, refactor, docs change, or operational change per issue.
- Keep commits atomic and issue-scoped. Prefer one coherent commit per child issue or per independently reviewable step inside that issue.
- Record important observations, commands, failures, design decisions, implementation notes, artifacts, verification, and residual risk as comments on the child issue.
- Close a child issue only after posting a detailed closeout comment with what changed, evidence, tests, commit refs, and remaining follow-up.
- Update the master issue when child issues are opened, materially change direction, resolve, or create follow-up work.
- Do not leave hanging work implicit. If any compatibility shim, migration, cleanup, temporary fallback, unresolved verification, operational risk, or "duct tape" remains, create or link a follow-up issue before saying the work is done.
Before Touching GitHub
Verify the actual repo and target issue surface:
git remote -v
gh repo view --json nameWithOwner,url
gh issue list --state all --limit 50
If the repo target is ambiguous, private/public boundaries are unclear, or the action would post to someone else's upstream repo, ask for confirmation before creating, commenting, closing, or editing issues. If a user fork exists and the user did not ask to post upstream, prefer the user's repo/fork.
Starting A Worklog
- Inspect existing issues before creating new ones.
- Reuse an existing master issue if it clearly owns the effort.
- Create a new master issue when no durable parent exists.
- For every distinct work item, create or identify a child issue and link it from the master issue.
- If the task already has code changes in progress, inspect
git statusand diffs before deciding issue boundaries.
What ships with it
1 file 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.
- 1mo ago First seen · 147 lines · 105 tokens per session scan A 5e6134c1b675
worklog is a skill published in the GitHub repository tokenbender/agent-guides (367 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,334 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
gsd-quick-batch
Batch several /skill:gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-pause-work
Create context handoff when pausing work mid-phase.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.