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 gpsaggese/helpers --skill project.update_progressgit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/project.update_progress)<a href="https://agentmods.dev/skills/gpsaggese/helpers/project.update_progress"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/project.update_progress/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/gpsaggese/helpers/project.update_progress"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/project.update_progress.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 | $0.00015 | $0.00784 |
| Opus 5.5 | $0.00006 | $0.00314 |
| Sonnet 5.5 | $0.00003 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
project.update_progress 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Given the plan ids of merged PR(s), sync the project docs: tick the plan, add the log entry, and record the decisions
- Log facts only. Never invent a result
Input
<PR_IDS>: One or more plan ids, e.g.,PR_M10<PR_NUM>: The GitHub PR number, optional- If missing, find the merged PR with
gh pr list --state merged --search "<PR_ID>"
- If missing, find the merged PR with
<DOCS_DIR>: The projectdocs/dir, optional- If missing, use
docs/in the current dir
- If missing, use
Workflow
Check the PR Is Merged
- Read the PR with
gh pr view <PR_NUM> - If the PR is not merged, stop and tell the user. A PR is checked only when merged
Update the Plan
- Tick
[x]the PR in the roadmap and in its entry in<DOCS_DIR>/04-plan.md - For a partly done PR, write its status in its entry. Do not tick it
- If the scope or order changed, edit the plan and log why in the progress log
Update the Log
- Add the entry to
<DOCS_DIR>/07-progress.md, after the older ones- Use a History row, or one section per PR when a row is too short
- Follow
.claude/skills/project.rules.mdsection "Write the Log" and the template.claude/templates/project_progress.template.md
- Take from the PR: the issue, the author, the UTC dates, the testing evidence, and the failing checks that the PR did not cause
- Update "Status", "Built", and "Next"
- Ask the user for any finding or number missing from the PR. Do not invent it
Record the Decisions
- For each decision in the PR description's "Decisions" section, add an entry to
<DOCS_DIR>/03-decisions.md- Follow
.claude/templates/project_decisions.template.md
- Follow
- Add a one-line pointer to the decision in the log entry
- Make the pointer a link to the
header in### `D<N>` (<Decision title>)03-decisions.md, per.claude/skills/project.rules.mdsection "Link Requirements and Decisions"
- Make the pointer a link to the
Sync the Other Docs
- Apply the event map in
.claude/skills/project.rules.mdsection "Map Each Event to the Doc to Update" - Update the design doc of each changed module
- Update
<DOCS_DIR>/README.mdif a doc was added, renamed, or removed - Add new terms to
<DOCS_DIR>/10-glossary.md, if the file exists
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 · 85 lines · 15 tokens per session scan A faa04e026bba
project.update_progress is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 784 once invoked, about $0.0001 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 2026-11-06.
project.update_progress compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| project.update_progressgpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 15 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |