Source profileQuality 77/100

wshobson/agents/plugins/skill-forge-essentials/skills/session-guard/SKILL.md

session-guard

Use when working on complex multi-step tasks, when a session is getting long (40+ tool calls), when the agent starts ignoring rules it followed earlier, when conventions drift, when output quality seems to degrade, or after any context compaction event. Prevents long-session corruption AND context compaction amnesia through behavioral self-enforcement.

Source repository stars
38,313
Declared platforms
0
Static risk flags
1
Last source update
2026-07-22
Source checked
2026-07-28
DecisionCompatibilityInstallWorkflowPermissionsEvidenceSource

Decision brief

What it does—and where it fits

Prevents long-session corruption AND context compaction amnesia through behavioral self-enforcement.

Best for

  • Session exceeds 40 tool calls
  • Agent contradicts earlier decisions
  • Style/naming conventions start drifting

Not for

  • Trusting that you remember the rules after 50+ tool calls (you don't - re-read)
  • Re-reading EVERYTHING to be safe (wastes tool calls - be targeted)

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/wshobson/agents --skill "plugins/skill-forge-essentials/skills/session-guard"
Safe inspection promptEditorial

Inspect the Agent Skill "session-guard" from https://github.com/wshobson/agents/blob/c4b82b0ad771190355eb8e204b1329732a18449a/plugins/skill-forge-essentials/skills/session-guard/SKILL.md at commit c4b82b0ad771190355eb8e204b1329732a18449a. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    When to Use

    Session exceeds 40 tool calls

    Session exceeds 40 tool callsAgent contradicts earlier decisionsStyle/naming conventions start drifting
  2. 02

    Health Signals

    Review the “Health Signals” section in the pinned source before continuing.

    Review and apply the “Health Signals” source section.
  3. 03

    Protocol

    Normal operation. No intervention needed.

    CHECKPOINT - summarize progress in one paragraphRECITE - state the 3-5 most critical active rules aloud: "Active rules: [naming convention], [file structure], [error handling pattern], [testing requirement]"ASSESS - almost done? Push through. Not done? Prepare split.
  4. 04

    Green Zone (0-40 tool calls)

    Normal operation. No intervention needed.

    Normal operation. No intervention needed.

Permission review

Static risk signals and limitations

Reads files

low · line 47

The documentation asks the agent to read local files, directories, or repositories.

RE-READ the project's rules file immediately

Reads files

low · line 50

The documentation asks the agent to read local files, directories, or repositories.

If uncertain about ANY prior decision, RE-READ the source file - don't guess

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score77/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars38,313SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
wshobson/agents
Skill path
plugins/skill-forge-essentials/skills/session-guard/SKILL.md
Commit
c4b82b0ad771190355eb8e204b1329732a18449a
License
MIT
Collected
2026-07-28
Default branch
main
View the original SKILL.md

Session Guard

Overview

Long sessions corrupt silently. Context compaction drops instructions unannounced. Hooks don't fix it (confirmed by multiple developers on GitHub issues #19471, #9796, #64171). This skill prevents both through behavioral self-enforcement: monitor health, anchor critical rules through compaction, split before damage occurs. No packages, no databases - pure behavioral enforcement that works in every harness.

When to Use

  • Session exceeds 40 tool calls
  • Agent contradicts earlier decisions
  • Style/naming conventions start drifting
  • After any context compaction event
  • Task scope growing unbounded

Health Signals

SignalThresholdAction
Tool call count>40YELLOW: checkpoint + recite critical rules
Tool call count>60RED: split or compact with anchor
Agent contradicts earlier decisionAnyVERIFY: re-read source of truth
Style/naming driftAnyRECITE: state the active rules aloud
File read returns unexpected contentAnyRE-READ: don't trust cached state
Task scope growing unboundedContinuousSPLIT: one task per session

Protocol

Green Zone (0-40 tool calls)

Normal operation. No intervention needed.

Yellow Zone (40-60 tool calls)

  1. CHECKPOINT - summarize progress in one paragraph
  2. RECITE - state the 3-5 most critical active rules aloud: "Active rules: [naming convention], [file structure], [error handling pattern], [testing requirement]"
  3. ASSESS - almost done? Push through. Not done? Prepare split.
  4. REDUCE - no exploratory reads. Only targeted operations.

Red Zone (60+ tool calls OR drift signal)

  1. STOP - do not make more tool calls
  2. VERIFY - re-read project rules (don't trust memory)
  3. CHECKPOINT - write state to handoff document
  4. SPLIT - create handoff, suggest fresh session

Context Anchoring (anti-compaction)

When compaction has occurred (sudden loss of earlier context, or after /compact):

  1. RE-READ the project's rules file immediately
  2. RECITE the 3-5 critical rules aloud in your response
  3. VERIFY your planned next action matches those rules before executing
  4. If uncertain about ANY prior decision, RE-READ the source file - don't guess

What survives compaction:

  • Most recent user messages (high priority)
  • Currently-invoked skill body (capped at 5K tokens, oldest dropped first)
  • Git status and project structure
  • File contents read AFTER compaction

What gets LOST in compaction:

  • Decisions made early in conversation
  • Architectural rules stated only verbally (not in files)
  • Context from tool outputs (file reads, command outputs)

Compaction-Safe Pattern

Keep critical instructions in FILES (CLAUDE.md, CONTEXT.md), NOT in conversation. If a rule matters, it must live in a file the agent can re-read - not in something agreed on earlier.

Common Mistakes

  • Trusting that you remember the rules after 50+ tool calls (you don't - re-read)
  • Re-reading EVERYTHING to be safe (wastes tool calls - be targeted)
  • Feeling fine therefore assuming context is fine (compaction is SILENT)
  • Splitting AFTER noticing problems (split BEFORE - prevention, not recovery)

Why This Matters

Context compaction is the #1 unsolved platform problem in 2026. Hooks don't fix it (confirmed: the agent ignores post-compaction injections because the compaction summary creates narrative momentum). This skill is the lightweight behavioral countermeasure: no infrastructure, no packages - disciplined self-monitoring that works in every harness.