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/endogenai/dogma/session-managementnpx skills add EndogenAI/dogma --skill session-managementgit clone --depth 1 https://github.com/EndogenAI/dogmaWrote 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/endogenai/dogma/session-management)<a href="https://agentmods.dev/skills/endogenai/dogma/session-management"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/session-management.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 | $0.00134 | $0.05009 |
| Opus 5 | $0.00067 | $0.02505 |
| Sonnet 5 | $0.00027 | $0.01002 |
| Haiku 4.5 | $0.00013 | $0.00501 |
Grade A, and why
session-management 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 4d 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 — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Management
This skill enacts the Algorithms Before Tokens axiom from MANIFESTO.md by encoding the full session lifecycle as a deterministic procedure. Session management is governed by AGENTS.md § Agent Communication — every rule in this skill derives from that section. Read AGENTS.md before deviating from any step below.
1. File Structure
The scratchpad lives in .tmp/ at the workspace root. It is gitignored and never committed.
.tmp/
<branch-slug>/ # branch name with / replaced by -
_index.md # one-line stubs of all closed sessions on this branch
<YYYY-MM-DD>.md # one file per session day — the active scratchpad
<branch-slug> examples:
- Branch
main→.tmp/main/ - Branch
feat/agent-skills→.tmp/feat-agent-skills/ - Branch
docs/update-guides→.tmp/docs-update-guides/
The _index.md accumulates single-line stubs for every closed session on the branch. Future sessions read it for fast orientation without opening old files.
2. Session Start
Context Snapshot Before Reset
Before calling prune_scratchpad.py --init during error recovery, save a snapshot of the current context:
uv run python scripts/prune_scratchpad.py --snapshot
This saves .tmp/<branch>/<date>-snapshot.yaml containing: task_name, task_parameters, timestamp, and active scratchpad section.
After re-entry into the failed task's decision point, compare contexts:
uv run python scripts/compare_context_snapshot.py \
--snapshot ".tmp/$(git branch --show-current | tr '/' '-')/$(date +%Y-%m-%d)-snapshot.yaml"
If equivalent: true → do not re-attempt. Escalate to user: "My context is identical to the failed attempt. New direction needed."
Encoding point: Research basis: docs/research/orchestrator-autopilot-failure.md § Recommendation 5. Scripts: scripts/prune_scratchpad.py --snapshot, scripts/compare_context_snapshot.py.
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.
- 4d ago First seen · 480 lines · 134 tokens per session scan A f3bb8bfa5bbd
session-management is a skill published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 134 tokens to every session and 5,009 once invoked, about $0.0007 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
auth-security
Secure authentication and authorization when credentials, sessions, roles, or permissions change.
karpathy-principles
Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
orloj-generator
Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…
api-design
Design or review REST/GraphQL APIs when endpoints or contracts change.
database-design
Design schemas and migrations when persistent data structures change.
doc-lookup
Check official docs when framework APIs or configuration may be version-sensitive.