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-research/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-research)<a href="https://agentmods.dev/skills/secure-ssid/hpe-networking-mcp/project-research"><img src="https://agentmods.dev/badge/skills/secure-ssid/hpe-networking-mcp/project-research/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-research"><img src="https://agentmods.dev/badge/skills/secure-ssid/hpe-networking-mcp/project-research.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 | $0.00041 | $0.00969 |
| Opus 5.5 | $0.00016 | $0.00388 |
| Sonnet 5.5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
project-research 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 2mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading a pika repository
Three things answer almost every question about what a repository requires,
none of them run a gate or write a byte: inspect_repo, read_contract, and
pika doctor/pika explain from a shell.
Where the durable state lives
| Path | What it is |
|---|---|
.project/contract.yaml |
The committed contract: profiles, per-slot verification commands, agent mappings, declared skill projections. Operator-owned; a schema error refuses to load rather than guessing. |
.project/profiles.lock |
The pinned digest of every pack the contract selects, against this binary's embedded registry. A mismatch means the lock and the binary disagree about what the packs are — not that the repository is broken. |
.project/exceptions.yaml |
Recorded naming deviations, one entry per path (or a list, for a path that violates more than one rule at once). Every record carries rule-id, reason, owner, review-condition — all four, or gate 1 fails on the record itself. |
.project/state/ |
Local, gitignored, transient: envelopes, run records, recovery journals. Never committed, never durable evidence. |
.project/evidence/<work-id>.json |
The kernel-issued receipt for one run: gates, exits, durations, the commit produced. Read this for what happened; do not write one. |
Reading the contract without a shell
read_contract (MCP) or pika doctor/cat .project/contract.yaml (shell)
loads the contract and resolves its profiles against the embedded pack
registry — the same resolution pika check uses, so what you read is what
will actually run. It reports:
- the profiles selected, in composition order (core first, one language pack at most);
- the effective command for every verification slot — the contract's own value where the contract sets one, else the pack's discovery hint;
- schema and profile-reference errors, rather than a partial guess.
A contract that does not parse is a fact to report, not a default to fall back on.
Reading the repository inventory
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.
- 2mo ago First seen · 84 lines · 41 tokens per session scan A 2c1360aa09d4
project-research is a skill published in the GitHub repository secure-ssid/hpe-networking-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 969 once invoked, about $0.0002 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 2026-09-05.
project-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| project-researchsecure-ssid/hpe-networking-mcp | Skill | 1 | 1mo ago | MIT | A | 41 | Claude Code, Codex |
| opik-diagnosecomet-ml/opik-mcp | Skill | 225 | 9d ago | Apache-2.0 | A | 187 | Claude Code |
| ue-mcp-epic-routingdb-lyon/ue-mcp | Skill | 476 | yesterday | MIT | A | 81 | Claude Code, Codex |
| qa-knowledgegriddynamics/rosetta | Skill | 370 | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| apitapn1byn1kt/apitap | Skill | 131 | 17d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| frontmcp-setupagentfront/frontmcp | Skill | 148 | yesterday | Apache-2.0 | A | 176 | Claude Code, Codex |
| x-use-reviewihuzaifashoukat/x-use | Skill | 181 | 4d ago | MIT | A | 56 | Claude Code |