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 agentmods add skills/adit-jain-srm/skill-forge/session-guardnpx skills add Adit-Jain-srm/skill-forge --skill session-guardgit clone --depth 1 https://github.com/Adit-Jain-srm/skill-forgeWrote 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/adit-jain-srm/skill-forge/session-guard)<a href="https://agentmods.dev/skills/adit-jain-srm/skill-forge/session-guard"><img src="https://agentmods.dev/badge/skills/adit-jain-srm/skill-forge/session-guard.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 | $0.00088 | $0.01233 |
| Opus 5 | $0.00044 | $0.00616 |
| Sonnet 5 | $0.00018 | $0.00247 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
session-guard 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Guard
Overview
Long sessions corrupt silently. Context compaction drops your instructions without warning. This skill prevents both: monitors health, anchors critical rules through compaction, and splits before damage occurs. No packages, no SQLite, no MCP — pure behavioral enforcement that works in Cursor AND Claude Code.
Process
Monitor session health passively. At checkpoints, RECITE critical rules to self-anchor. Split BEFORE corruption appears — once it occurs, it's invisible and irreversible.
Persistence
ACTIVE every session. Monitors passively. Escalates on threshold breach. Recites critical rules at checkpoints.
The Problem (June 2026, confirmed across platforms)
Two distinct failure modes:
1. Tool Call Degradation (50+ calls):
- Hallucinated tool results (content that doesn't match files on disk)
- Tool results duplicated (same read echoed 2-8x)
- False progress (agent claims "done" for incomplete work)
2. Context Compaction Amnesia:
- CLAUDE.md instructions silently dropped after compaction
- Naming conventions, architectural rules, file structure constraints forgotten
- Agent operates from "degraded mental model" without knowing it
- Compaction summary creates "narrative momentum" that overrides re-injected rules
Both are PLATFORM limitations. Smart session management mitigates both completely.
Health Signals
| Signal | Threshold | Action |
|---|---|---|
| Tool call count | >40 | YELLOW: checkpoint + recite critical rules |
| Tool call count | >60 | RED: split or compact with anchor |
| Agent contradicts earlier decision | Any | VERIFY: re-read source of truth |
| Style/naming conventions drift | Any | RECITE: state the active rules aloud |
| File read returns unexpected content | Any | RE-READ: don't trust cached state |
| Repeated failed tool calls | 3+ same error | PAUSE: diagnose before continuing |
| Task scope growing unbounded | Continuous | SPLIT: one task per session |
Protocol
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 · 130 lines · 88 tokens per session scan A 255b7c725adf
session-guard is a skill published in the GitHub repository Adit-Jain-srm/skill-forge (2 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,233 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
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
user-research-cookiy
End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design, usability studies, participant recruitment…
daily-journal
A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /daily-journal, say…
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
ijfw-handoff
Session handoff generation and loading. Trigger: session end, context full, /handoff.