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-maintain/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-maintain)<a href="https://agentmods.dev/skills/secure-ssid/hpe-networking-mcp/project-maintain"><img src="https://agentmods.dev/badge/skills/secure-ssid/hpe-networking-mcp/project-maintain/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/secure-ssid/hpe-networking-mcp/project-maintain"><img src="https://agentmods.dev/badge/skills/secure-ssid/hpe-networking-mcp/project-maintain.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 | $0.00051 | $0.01245 |
| Opus 5 | $0.00026 | $0.00622 |
| Sonnet 5 | $0.00010 | $0.00249 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
project-maintain 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keeping a repository current with its pika
Two kinds of drift show up as a red gate 1, and they have different remedies: the repository's pinned pack digests can fall behind the binary (or run ahead of it), and a generated projection can fall behind the canonical skill or guidance it was rendered from. Neither is fixed by editing the failing file by hand.
profiles.lock drift
.project/profiles.lock pins the digest of every pack the contract selects.
Gate 1 recomputes those digests against the running binary's embedded
registry and fails on disagreement, printing both numbers:
profiles.lock: profiles.lock records registry digest e824...2fdf, and this
pika's embedded pack registry is f34a...9e9e. ... establish which side is
behind before regenerating.
Establish which side is behind before running anything. The two causes
have opposite remedies, and the wrong one is silent: pika init --force run
from an older binary rewrites a correct lock to pin older packs, and gate 1
then reports green on a downgraded repository.
pika version --root . # does THIS binary's registry match the lock?
which -a pika # any other pika on this machine?
git log -1 -- .project/profiles.lock # who wrote the lock, and when
If some other installed pika matches the lock's digest, that build wrote
it and the one that failed is behind — upgrade or rebuild, then re-run
pika check --all. Nothing in the repository needs to change.
If the lock is genuinely the stale side, the remedy is one command, and it costs nothing you wrote:
git status --porcelain # clean tree first, so the diff below is only this command
pika init --force # profiles, name and module are read back from the repository
git diff # the contract, the lock, the PR template, the CI workflow — nothing else
pika check --all # gate 1 goes green again
What --force touches, and what it never does
--force regenerates only what the kernel owns: .project/contract.yaml,
.project/profiles.lock, .github/pull_request_template.md, and
.github/workflows/ci.yml. Everything else it scaffolds — README.md,
AGENTS.md, CONTRIBUTING.md, the language scaffold, the canonical skills
under .agents/skills/ — is written only where it is missing, exactly as
pika apply's create-if-missing path already treats them. A project that
has tuned its own skill or edited its own docs does not lose them to an
upgrade. --reset-docs (only alongside --force) is the one opt-in that
restores the scaffold's own text over yours, docs and skills alike; nothing
else does, and no flag ever touches .project/exceptions.yaml.
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 · 114 lines · 51 tokens per session scan A 343fb886dfbe
project-maintain is a skill published in the GitHub repository secure-ssid/hpe-networking-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 1,245 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 2026-09-05.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, then fills the gaps with list (filters, sort, a time…
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
mcp-google-map-project
Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.
frontmcp-setup
Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…