Borrowing it
Nothing to install: this file belongs to secure-ssid/hpe-networking-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/secure-ssid/hpe-networking-mcp/main/.agents/skills/project-work/SKILL.mdgit clone --depth 1 https://github.com/secure-ssid/hpe-networking-mcpWrote 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/secure-ssid/hpe-networking-mcp/project-work)<a href="https://agentmods.dev/skills/secure-ssid/hpe-networking-mcp/project-work"><img src="https://agentmods.dev/badge/skills/secure-ssid/hpe-networking-mcp/project-work.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00836 |
| Opus 5 | $0.00018 | $0.00418 |
| Sonnet 5 | $0.00007 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
project-work 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving pika
pika is a kernel that decides whether your changes are safe to keep. You propose; it verifies and commits. Nothing you assert counts as evidence — only a green verification ladder does.
Pick the command
| Situation | Command |
|---|---|
| Checks are failing and you want them fixed | pika improve |
| You have a goal to implement | pika work "<goal>" |
| A previous run was interrupted | pika resume <work-id> |
| A run or transaction was killed and left a lock | pika recover --apply |
| You want to know what is wrong before acting | pika doctor |
| You do not understand a rule, gate, or error code | pika explain <id> |
pika status lists runs. pika status <work-id> shows one in full.
The loop
improve and work do the same thing, differing only in what starts them:
- run the ladder (
pika check) - hand only the failing gates to the configured agent — warnings never go
- re-run the ladder against what the agent produced
- commit on a branch only if the recheck is green
You are step 3's subject, not its judge. The kernel re-verifies independently.
Rules that are not obvious
The ladder is the evidence. A green pika check is the only completion
signal. Never report done from a narrative, a diff that looks right, or a test
you ran by hand.
blocked means diagnose, not retry. A blocked run recorded a reason. Read
it with pika status <work-id>. Re-running without changing anything reproduces
the same block.
A refusal naming another holder means someone else is writing. A run-lease
refusal or scope_conflict means a second process holds this repository — one
repository runs one run at a time, because both would commit through the same
working tree. Do not loop, do not wait, and never delete a lock file.
pika recover clears only a holder it can prove is dead; a holder on another
machine is reported unverifiable and is never swept.
Never commit .project/state/. It holds prompts, check reports, and briefly
the raw agent transcript. The kernel filters it out of commits — do not defeat
that by moving, renaming, or copying content out of it.
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.
- 2d ago First seen · 79 lines · 37 tokens per session scan A 40185dc3c678
project-work is a skill published in the GitHub repository secure-ssid/hpe-networking-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 836 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 2026-09-05.
Other skills, from other repositories
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
meta-pre-commit-quality-gate
Run three quality gates (ruff + mypy + pytest) in parallel over the staged diff, then arbitrate a single BLOCK/APPROVE verdict. Use before committing changes locally when you want a comprehensive pre-commit gate beyond per-file linting — exactly the same gate set CI enforces.
nw-quality-framework
Quality gates - 11 commit readiness gates, build/test protocol, validation checkpoints, and quality metrics.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
Changelog Test Mapper
Map changelog entries and release notes to affected test cases, ensuring every user-facing change has corresponding test coverage verification.