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 instructions/rjmurillo/ai-agents/session-logsgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/instructions/rjmurillo/ai-agents/session-logs)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/session-logs"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/session-logs.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 | $0.01069 | $0.01069 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
ai-agents session-logs.instructions.md 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Log Mechanics
.agents/schemas/session-log.schema.json describes what a session log
contains. Session log creation is discontinued: do not create a new
.agents/sessions/*.json file. Nothing ever required one to commit, push, or
open a PR. The existing logs under .agents/sessions/ stay in the repository
as history and remain readable by the retrospective skill, memory
extraction, and the PreCompact hook. This rule covers the mechanics that still
apply to a log that already exists on your branch (carried over from before
this change, or cherry-picked from an older one).
Scoped to .agents/** rather than ** on purpose. The mechanics matter only
when a change touches that tree, and the always-on instruction ceiling
(scripts/validation/instruction_budget.py) has under 500 bytes of headroom, so
a universally scoped copy would block the next contributor's rule. Note that the
generator currently ships this rule to the plugin with applyTo: '**', because
.agents/** is filtered as internal-only and the empty scope is backfilled as
universal; that is issue #4317, not a property of this rule.
MUST
-
Do not create a new session log. Session log creation is discontinued; no start, end, commit, push, or PR gate ever required one, and none does now. If a log named
.agents/sessions/YYYY-MM-DD-session-NN<slug>.jsonends up staged anyway (for example, cherry-picked from an older branch), thesession-policypre-commit hook still validates it (scripts/validation/git_hook_policy.py session, a validate-if-present gate): a malformed log still blocks that commit. When no log is staged, the gate returns 0 (check_sessionspasses when there are no session paths, and also when_merge_in_progress). -
Record
endingCommitin a follow-up commit, never by amending. Amending replaces the commit whose SHA the log names, sovalidate_session_json.pythen reports the recorded SHA as unreachable (issue #3618). Commit the work withendingCommitempty, then commit the SHA in a second commit. The reachability check returns no finding in a shallow clone (session_scope.pyshort-circuits when--is-shallow-repositoryis true), so a green CI run on a shallow checkout is not evidence the SHA is reachable.
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.
- yesterday First seen · 77 lines · 1,069 tokens per session scan A d96d4f5cc14a
ai-agents session-logs.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 1,069 tokens to every session, about $0.0053 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 instructions, from other repositories
claude-capsule-kit CLAUDE.md
Instructions for arpitnath/claude-capsule-kit, covering capsule kit v4.0, rules, context system (capsule), wikilink layer and docs.
ClawAI CLAUDE.md
Claude Code instructions for ihabkhaled/ClawAI, covering clawai — root policy, identity, authority hierarchy (higher wins on conflict), first command, always and work arriving as a document.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.