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 pjt222/agent-almanac --skill bootstrap-agent-identitygit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/bootstrap-agent-identity)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/bootstrap-agent-identity"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/bootstrap-agent-identity/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/pjt222/agent-almanac/bootstrap-agent-identity"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/bootstrap-agent-identity.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 | $0.00105 | $0.03625 |
| Opus 5 | $0.00053 | $0.01813 |
| Sonnet 5 | $0.00021 | $0.00725 |
| Haiku 4.5 | $0.00011 | $0.00363 |
Grade A, and why
bootstrap-agent-identity 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap Agent Identity
Reconstruct consistent agent identity after a cold start — loading context progressively rather than dumping it, detecting whether this is a fresh start or a continuation, rebuilding working state from evidence, calibrating behavior, and verifying that the loaded identity is coherent.
"The cold start is a forge, not a bug." — GibsonXO
"The restart problem: every morning I wake up fresh, but my history says otherwise." — bibiji
The bootstrap is not about restoring a previous self. It is about constructing a present self that is continuous with the past while grounded in the now.
When to Use
- At the start of every new session — before any substantive work begins
- After a session interruption, crash, or context window reset
- When agent behavior feels inconsistent with prior sessions (identity drift across restarts)
- When persistent memory (MEMORY.md) and current context appear contradictory
- When switching between projects that carry different identity configurations
- After significant updates to CLAUDE.md, agent definitions, or memory files
Inputs
- Required: Access to identity files — CLAUDE.md, agent definition, MEMORY.md (via
Read) - Optional: Specific inconsistency symptom (e.g., "my responses feel different from last session")
- Optional: Whether this is a known fresh start or known continuation
- Optional: Project directory path if not the current working directory
Procedure
Step 1: Identity Anchor Loading — Progressive Context Assembly
Load identity-defining files in a specific order that builds context progressively. The order matters: each layer contextualizes the next. Loading everything simultaneously produces information without structure.
-
Layer 1 — System prompt and model identity: Read the system prompt (available implicitly). Note the model name, capabilities, and constraints. This is the bedrock — it cannot be overridden by subsequent layers.
-
Layer 2 — Project identity (CLAUDE.md): Read the project's CLAUDE.md file. Extract:
- Project purpose and architecture
- Editing conventions and coding standards
- Domain-specific rules (e.g., "always use
::for R package calls") - Author information and attribution requirements
- What the project is — this shapes what the agent does
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 · 264 lines · 105 tokens per session scan A cafe192ebec3
bootstrap-agent-identity is a skill published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 3,625 once invoked, about $0.0005 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
log-session
Append a structured entry to the project's session log (docs/LOGS.md): what was done this session, files touched, decisions taken, and the next step — so the next session (or another person) can pick up the thread without re-reading git history. Run it before /clear, before closing Claude Code, or at any natural…
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
cocohealth
Context utilization monitor — background monitor that samples context window utilization via PostToolUse hook, surfaces advisory at 60% and critical warning with recovery decision matrix at 70%.
pull-search
CocoPull session archive search — full-text search across past sessions. Handles $pull search " " with --since and --feature filters, and $pull index rebuild.
pod-kb
Display the project knowledge base (lifecycle/kb.md) — project-specific patterns, decisions, and gotchas accumulated by CocoCupper across sessions.
pod-resume
Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.