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 PlamenTSV/plamen --skill gossip-cache-invariancegit clone --depth 1 https://github.com/PlamenTSV/plamenWrote 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/plamentsv/plamen/gossip-cache-invariance)<a href="https://agentmods.dev/skills/plamentsv/plamen/gossip-cache-invariance"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/gossip-cache-invariance/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/plamentsv/plamen/gossip-cache-invariance"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/gossip-cache-invariance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.00854 |
| Opus 5 | $0.00015 | $0.00427 |
| Sonnet 5 | $0.00006 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
gossip-cache-invariance 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 6d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Injectable Skill: Gossip Cache Invariance
L1 trigger:
P2Pflag AND (seen_cache,message_cache,tx_cache,gossipsub,pubsub,dedup,seen_chunksdetected) Inject Into:depth-network-surface,depth-consensus-invariantLanguage: Go and Rust Finding prefix:[GCI-N]
1. Write-After-Validate
For each attacker-controlled cache key, prove the ordering between cache write and integrity/authenticity validation. Cache insertion before validation is a poisoning primitive.
Tag: [GOSSIP-CACHE:ORDER]
2. Duplicate Handling
Check whether duplicate suppression is keyed on canonical content, the right topic/partition, and enough sender identity. Look for cases where legitimate messages are suppressed or malicious messages can be replayed after eviction.
Tag: [GOSSIP-CACHE:DUPLICATES]
3. Eviction Invariants
Under burst traffic or memory pressure:
- what gets evicted first?
- can attacker traffic evict honest messages before processing?
- can eviction reopen a previously rejected malicious message?
Tag: [GOSSIP-CACHE:EVICTION]
4. Cache Key Soundness
Verify the key includes the right tuple of topic / partition / chain / message identity. Flag collisions where distinct messages alias to the same cache key.
Tag: [GOSSIP-CACHE:KEY]
5. Broken Safety Property
State the resulting invariant failure explicitly:
- valid message can be suppressed
- invalid message can block later valid message
- message can be processed repeatedly
- attacker can force honest work without progress
6. Cache-miss amplification
For each receive-and-rebroadcast path:
- Does the handler consult a seen/validated cache before re-broadcast?
- Is the cache key canonical, or can the attacker create many distinct IDs for effectively the same payload?
- If the cache misses, does one inbound message cause fan-out to many peers?
If a cache miss multiplies traffic or work across peers, record it as an amplification finding rather than a simple duplicate-handling bug.
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.
- 6d ago First seen · 96 lines · 29 tokens per session scan A b0ae17d7e639
gossip-cache-invariance is a skill published in the GitHub repository PlamenTSV/plamen (295 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 854 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
django-drf
Django REST Framework patterns. Trigger: When implementing generic DRF APIs (ViewSets, serializers, routers, permissions, filtersets). For Prowler API specifics (RLS/RBAC/Providers), also use prowler-api.
django-migration-psql
Reviews Django migration files for PostgreSQL best practices specific to Prowler. Trigger: When creating migrations, running makemigrations/pgmakemigrations, reviewing migration PRs, adding indexes or constraints to database tables, modifying existing migration files, or writing data backfill migrations. Always use…
prowler-api
Prowler API patterns: RLS, RBAC, providers, Celery tasks. Trigger: When working in api/ on models/serializers/viewsets/filters/tasks involving tenant isolation (RLS), RBAC, or provider lifecycle.
prowler-changelog
Manages changelog entries for Prowler components following keepachangelog.com format. Trigger: When creating PRs, adding changelog entries, or working with any CHANGELOG.md file in ui/, api/, mcpserver/, or prowler/.
jsonapi
Strict JSON:API v1.1 specification compliance. Trigger: When creating or modifying API endpoints, reviewing API responses, or validating JSON:API compliance.
prowler-test-api
Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).