Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/darthzen/fossa-mcp/fossa-spec-drift)<a href="https://agentmods.dev/skills/darthzen/fossa-mcp/fossa-spec-drift"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-spec-drift/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/darthzen/fossa-mcp/fossa-spec-drift"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-spec-drift.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 | $0.00081 | $0.02938 |
| Opus 5 | $0.00041 | $0.01469 |
| Sonnet 5 | $0.00016 | $0.00588 |
| Haiku 4.5 | $0.00008 | $0.00294 |
Grade A, and why
fossa-spec-drift 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 9d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fossa-spec-drift
Snapshot the vendored spec, fetch the live one, diff them at the operation level, and say which of the differences land on a tool this server actually registers. The output is a report, not a commit: the working tree is put back the way it was found unless the user says otherwise.
Why the diff is operation-level: the spec is 1.4 MB of pretty-printed JSON. A text diff drowns in key-order and formatting churn and cannot tell a doc-string tweak from a removed parameter. Comparing the parsed JSON path-by-path gives three clean lists — added, removed, changed — and "changed" is defined as parameters, request body, or responses differing. Nothing else counts as drift.
Everything below is procedure; the only question worth asking first is whether the user wants the report only (default) or also wants the new spec kept.
1. Snapshot the baseline
All commands run from the repo root:
/Users/rashford/Library/Mobile Documents/com~apple~CloudDocs/Developer/fossa-mcp
— quote the path, it contains spaces.
First confirm the baseline exists. What is tracked on the current branch is
decided by git ls-files spec/ API_PARITY_PLAN.md and by nothing else — a
per-branch inventory hardcoded into this file went stale the same day it was
written. If spec/fossa-openapi.json is not in that output, there is no drift
to measure — say so, and note that running the update script (step 2)
establishes a baseline for next time.
$SCRATCHPAD is not predefined — in a fresh shell the cp below would target
/spec-baseline.json and fail. Set it to the session scratchpad directory if
one is listed, otherwise mktemp -d, and since shell state does not persist
between commands, use the same absolute path in every later step.
SCRATCHPAD="${SCRATCHPAD:-$(mktemp -d)}"
cp spec/fossa-openapi.json "$SCRATCHPAD/spec-baseline.json"
python3 -c "
import json
s = json.load(open('spec/fossa-openapi.json'))
M = {'get','put','post','delete','patch','options','head','trace'}
print(s['info']['version'],
sum(1 for item in s['paths'].values() for m in item if m in M), 'operations')
"
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.
- 9d ago First seen · 246 lines · 81 tokens per session scan A 218828e77629
fossa-spec-drift is a skill published in the GitHub repository darthzen/fossa-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,938 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
platform-apex-generate
Primary Apex authoring skill for class generation, refactoring, and review. ALWAYS ACTIVATE when the user mentions Apex, .cls, triggers, or asks to create/refactor a class (service, selector, domain, batch, queueable, schedulable, invocable, DTO, utility, interface, abstract, exception, REST resource). Use this skill…
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
api-contract-review
Use when auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests, especially during periodic quality review or before preparing corrective PRs.
principle-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
api-reviewer
A review of an API contract, the agreed description of how software systems exchange requests, responses, events, or files.